Paper Citation Record · LEDGER

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding

As of 16 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 3 inbound Pith citation observations for arXiv:2507.22928.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2507.22928 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:21:13.021612Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T00:23:50.436202Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

42 of 42 outbound references displayed

verified exact2
verified fuzzy0
unresolved39
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 589de791-c76f-43cd-8f54-3e9053be49ce · outbound

This paper cites , " * write output.state after.block = add.period write newline.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding , " * write output.state after.block = add.period write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.861030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cba9de4-e288-4b6a-a03b-22af76670bf0 · outbound

This paper cites write newline.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.865106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 106c5eff-deb8-4ab6-bc70-350596a3e86b · outbound

This paper cites Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.869648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b03b5c8c-4166-4d74-8ec5-fd57b9eb772e · outbound

This paper cites Faithfulness Tests for Natural Language Explanations.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Faithfulness Tests for Natural Language Explanations

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.873916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78812c5a-0f7a-42f8-bf0a-e3bcb12a2722 · outbound

This paper cites an unresolved cited work.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.878718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6a19327-babd-4d79-942c-b6ca9de3979d · outbound

This paper cites Mechanistic Interpretability for AI Safety -- A Review.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Mechanistic Interpretability for AI Safety -- A Review

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.882758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13ba8ede-40fb-478f-9649-b849430f5504 · outbound

This paper cites an unresolved cited work.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.886688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b252c6dd-a085-447d-84a0-45df8c31833c · outbound

This paper cites an unresolved cited work.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:21:13.695349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 61588e45-37d7-460e-a66d-4d184a866645 · outbound

This paper cites an unresolved cited work.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.894293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 459d7a01-4595-4e8a-b906-e9afa15921a1 · outbound

This paper cites an unresolved cited work.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.897903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation def9c75a-a17d-475b-a93b-b8aef5fe897a · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Training Verifiers to Solve Math Word Problems

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.903109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 168f8ef2-7449-45bf-80ee-9b7cb38b18a5 · outbound

This paper cites Sparse Autoencoders Find Highly Interpretable Features in Language Models.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.906793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6ca6c23-b91a-41c4-af27-5b27f1d34dc7 · outbound

This paper cites Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.910702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 485cd831-2509-4d88-939e-77bf015a0b33 · outbound

This paper cites Tokenized SAEs: Disentangling SAE Reconstructions.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Tokenized SAEs: Disentangling SAE Reconstructions

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.914460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b685728-a967-4ea0-8ae6-1d06d751be4c · outbound

This paper cites How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.918891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35ad841d-6112-4508-badd-4358206a5a3d · outbound

This paper cites Toy Models of Superposition.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Toy Models of Superposition

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.922606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7dee443-348d-4baa-98ad-9c9fe9f2a572 · outbound

This paper cites Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.926237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d950279e-504f-4308-987a-7645c75dc822 · outbound

This paper cites an unresolved cited work.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:21:13.677354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7b5b762f-7987-4fcb-863c-05c41b7b873e · outbound

This paper cites an unresolved cited work.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:21:13.666656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 25152b33-d5e2-4a7f-9ede-46a2cef824ca · outbound

This paper cites Localizing Model Behavior with Path Patching.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Localizing Model Behavior with Path Patching

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.936927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e151c6df-458c-4509-a624-7cfb9d0b00bb · outbound

This paper cites an unresolved cited work.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:21:13.655664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fb418409-32c5-4df7-8c80-eac30f3b189e · outbound

This paper cites How to use and interpret activation patching.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding How to use and interpret activation patching

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.944225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f992757-a0f2-4c94-8baf-fd3dd9143563 · outbound

This paper cites Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.948006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11333139-959c-4dae-8959-2d3e5f45c216 · outbound

This paper cites S.; Reid, M.; Matsuo, Y.; and Iwasawa, Y.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding S.; Reid, M.; Matsuo, Y.; and Iwasawa, Y

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.951668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cc4ecbe-6206-473b-ac57-528640a35ad9 · outbound

This paper cites Leveraging LLMs for Hypothetical Deduction in Logical Inference: A Neuro-Symbolic Approach.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Leveraging LLMs for Hypothetical Deduction in Logical Inference: A Neuro-Symbolic Approach

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.955346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3eb7d61f-4e0e-4ed5-ae7c-019584a9d4df · outbound

This paper cites Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.958974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 697195d0-f591-491d-b3d1-f19c8100bd5c · outbound

This paper cites Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.963135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ef01f3c-ed5d-45e6-944d-fe60c2148131 · outbound

This paper cites Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.966829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54ef891a-87aa-411a-a459-061e9adbc338 · outbound

This paper cites an unresolved cited work.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.970470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23463316-1fb9-47ce-a4bc-ba00203caec3 · outbound

This paper cites Analyzing (In)Abilities of SAEs via Formal Languages.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Analyzing (In)Abilities of SAEs via Formal Languages

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-08-15T18:21:13.222900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0035dd49-a209-46dc-8421-0ac66948edcc · outbound

This paper cites Progress measures for grokking via mechanistic interpretability.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Progress measures for grokking via mechanistic interpretability

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.977751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c52bc77d-6ced-4579-a42f-72044479ff24 · outbound

This paper cites Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.982072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba748365-a235-45b5-804d-54fc01958b25 · outbound

This paper cites an unresolved cited work.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.985706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb4680d5-af6c-4c09-95b2-3720a02b48df · outbound

This paper cites an unresolved cited work.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:21:13.631586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e031bf3b-b3fc-4283-a6ba-816988a247eb · outbound

This paper cites The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models

Reference 35

Resolution: metadata mismatch; local_arxiv, observed 2026-08-15T18:21:13.124489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 3fe42dd0-8a06-4ff8-a738-a41e1a05585c · outbound

This paper cites Probing Language Models on Their Knowledge Source.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Probing Language Models on Their Knowledge Source

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-08-15T18:21:13.109366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 38e2da06-e909-45a2-ae9a-51d3dd12b152 · outbound

This paper cites V.; Zhou, D.; et al.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding V.; Zhou, D.; et al

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:13.002452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 246d8e9a-f30e-48ba-a294-583f0470e090 · outbound

This paper cites A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:13.006013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77d34e41-ec87-4778-9277-ae9e8c4fa7c1 · outbound

This paper cites Faithful Logical Reasoning via Symbolic Chain-of-Thought.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Faithful Logical Reasoning via Symbolic Chain-of-Thought

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:13.009786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c936717b-1635-4f66-9174-7e9e582abf1a · outbound

This paper cites Dissociation of Faithful and Unfaithful Reasoning in LLMs.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Dissociation of Faithful and Unfaithful Reasoning in LLMs

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:13.013526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49c888dd-6035-4b3b-87a5-a271be3a721f · outbound

This paper cites Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:13.017376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65cb181a-6b30-493e-b970-ff4b516736f0 · outbound

This paper cites Towards Best Practices of Activation Patching in Language Models: Metrics and Methods.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Towards Best Practices of Activation Patching in Language Models: Metrics and Methods

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:13.021612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation d3757901-b926-4635-8ef6-a6577f73d58e · inbound

The Tell-Tale Norm: $\ell_2$ Magnitude as a Signal for Reasoning Dynamics in Large Language Models cites this paper.

The Tell-Tale Norm: $\ell_2$ Magnitude as a Signal for Reasoning Dynamics in Large Language Models How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-07-02T12:26:56.910598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bb601e90-db41-492e-a2db-e7cb53e512f7 · inbound

Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces cites this paper.

Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding

Reference 88

Resolution: verified exact; arxiv_id, observed 2026-06-27T22:31:21.457839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 33f4f543-12ee-479c-82d3-1435710c04de · inbound

Thinking vs. NoThinking: Towards Interpreting Reasoning Mechanisms of Large Language Models via Sparse Autoencoders cites this paper.

Thinking vs. NoThinking: Towards Interpreting Reasoning Mechanisms of Large Language Models via Sparse Autoencoders How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T00:23:50.436202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.