Paper Citation Record · LEDGER

Understanding sparse autoencoder scaling in the presence of feature manifolds

As of 17 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 5 inbound Pith citation observations for arXiv:2509.02565.

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

pith.paper-citation-record.v1
2509.02565 v2

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T16:41:17.984961Z

measured 40 of 40 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 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-29T08:39:14.327838Z

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

35 of 35 outbound references displayed

verified exact1
verified fuzzy10
unresolved24
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

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

Outbound references

Observation 3af68547-824a-4abb-b3f6-7766a5492011 · outbound

This paper cites Sparse autoencoder.

Understanding sparse autoencoder scaling in the presence of feature manifolds Sparse autoencoder

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.828845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e5361c4-61b9-4b93-8347-2a76ad88b0f2 · outbound

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

Understanding sparse autoencoder scaling in the presence of feature manifolds Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.833953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fe99f32-cb02-4921-8e66-a82f616ba957 · outbound

This paper cites Towards monosemanticity: Decomposing language models with dictionary learning.

Understanding sparse autoencoder scaling in the presence of feature manifolds Towards monosemanticity: Decomposing language models with dictionary learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.839335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 697a7e59-c499-4f95-868b-b0226efde245 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Understanding sparse autoencoder scaling in the presence of feature manifolds Scaling and evaluating sparse autoencoders

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.844028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24cd8b4c-fbaa-4b83-9247-c80e055e33a3 · outbound

This paper cites Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders.

Understanding sparse autoencoder scaling in the presence of feature manifolds Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.848897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eaebf6d6-4c18-4218-82e9-b0cae5124e14 · outbound

This paper cites BatchTopK Sparse Autoencoders.

Understanding sparse autoencoder scaling in the presence of feature manifolds BatchTopK Sparse Autoencoders

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.853417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 620a6511-9548-4b76-b5be-3f92e8d0ed9b · outbound

This paper cites Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models.

Understanding sparse autoencoder scaling in the presence of feature manifolds Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.858258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 696e63e5-4a6c-416b-8975-eb223f8695bd · outbound

This paper cites Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures.

Understanding sparse autoencoder scaling in the presence of feature manifolds Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.862490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b023f786-c1c2-4578-b66e-aec9bd9dacc7 · outbound

This paper cites From flat to hierarchical: Extracting sparse representations with matching pursuit.

Understanding sparse autoencoder scaling in the presence of feature manifolds From flat to hierarchical: Extracting sparse representations with matching pursuit

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.867229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff8f7b78-007a-47b6-85d2-7ee6f6e2004a · outbound

This paper cites Transcoders find interpretable llm feature circuits.

Understanding sparse autoencoder scaling in the presence of feature manifolds Transcoders find interpretable llm feature circuits

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:41:18.779100Z

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 98e4c637-62f6-42e7-8711-f5116838e124 · outbound

This paper cites Sparse crosscoders for cross-layer features and model diffing, October 2024.

Understanding sparse autoencoder scaling in the presence of feature manifolds Sparse crosscoders for cross-layer features and model diffing, October 2024

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:41:18.763155Z

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 14d75827-d352-4838-8d41-c3401f5c31cf · outbound

This paper cites Group Crosscoders for Mechanistic Analysis of Symmetry.

Understanding sparse autoencoder scaling in the presence of feature manifolds Group Crosscoders for Mechanistic Analysis of Symmetry

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-08-15T16:41:18.423577Z

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 e55c8d20-2d29-4f58-9720-c10f389d7bee · outbound

This paper cites Robustly identifying concepts introduced during chat fine-tuning using crosscoders.

Understanding sparse autoencoder scaling in the presence of feature manifolds Robustly identifying concepts introduced during chat fine-tuning using crosscoders

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.885499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88caa5b9-b445-4bd9-8169-f5e6092e952b · outbound

This paper cites an unresolved cited work.

Understanding sparse autoencoder scaling in the presence of feature manifolds Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.889860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b001bb1-3f2a-4bc7-9116-755eb49c5cef · outbound

This paper cites Daniel Freeman, Theodore R.

Understanding sparse autoencoder scaling in the presence of feature manifolds Daniel Freeman, Theodore R

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.894338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e6546aa-436b-482c-a420-8df54b01a64f · outbound

This paper cites Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2.

Understanding sparse autoencoder scaling in the presence of feature manifolds Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.898987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9aa900e2-dd74-446a-b729-3620ee2c4933 · outbound

This paper cites an unresolved cited work.

Understanding sparse autoencoder scaling in the presence of feature manifolds Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:41:18.726864Z

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 f12465cd-3e1a-4e94-ab8e-de3766466899 · outbound

This paper cites Scaling laws for dictionary learning, April 2024.

Understanding sparse autoencoder scaling in the presence of feature manifolds Scaling laws for dictionary learning, April 2024

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:41:18.710910Z

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 1c93900e-c762-4afa-8169-8f796bcf1ebe · outbound

This paper cites The dark matter of neural networks? Transformer Circuits Thread, July 2024.

Understanding sparse autoencoder scaling in the presence of feature manifolds The dark matter of neural networks? Transformer Circuits Thread, July 2024

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:41:18.695412Z

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 4d85f121-2957-482e-8de5-c751fb6d4f24 · outbound

This paper cites Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations.

Understanding sparse autoencoder scaling in the presence of feature manifolds Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.917288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f90ad7d1-f4a7-4204-8374-050ab2b9aaaf · outbound

This paper cites Projecting assumptions: The duality between sparse autoencoders and concept geometry.

Understanding sparse autoencoder scaling in the presence of feature manifolds Projecting assumptions: The duality between sparse autoencoders and concept geometry

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.922234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57afb69c-33db-495f-9a62-2aa63a6f8628 · outbound

This paper cites Not All Language Model Features Are One-Dimensionally Linear.

Understanding sparse autoencoder scaling in the presence of feature manifolds Not All Language Model Features Are One-Dimensionally Linear

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.926938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a3b619f-5979-481f-8ecf-b4805c048e0e · outbound

This paper cites The Origins of Representation Manifolds in Large Language Models.

Understanding sparse autoencoder scaling in the presence of feature manifolds The Origins of Representation Manifolds in Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.931527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bb8bc4c-84e1-4924-a341-2a32bc3368da · outbound

This paper cites Decomposing The Dark Matter of Sparse Autoencoders.

Understanding sparse autoencoder scaling in the presence of feature manifolds Decomposing The Dark Matter of Sparse Autoencoders

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.936229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbbbc509-e555-49f5-b7a7-67536c77bcdd · outbound

This paper cites Neural Scaling Laws Rooted in the Data Distribution.

Understanding sparse autoencoder scaling in the presence of feature manifolds Neural Scaling Laws Rooted in the Data Distribution

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.941064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acaae035-2f28-4c48-bab0-27f29c25fe56 · outbound

This paper cites Toy models of superposition.

Understanding sparse autoencoder scaling in the presence of feature manifolds Toy models of superposition

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:41:18.681348Z

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 cda7aa24-42c3-4ffa-8ae3-089446d79f02 · outbound

This paper cites A is for absorption: Studying feature splitting and absorption in sparse autoen- coders.

Understanding sparse autoencoder scaling in the presence of feature manifolds A is for absorption: Studying feature splitting and absorption in sparse autoen- coders

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.950634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 577da0a0-2814-45b7-b6a4-08fff71f03de · outbound

This paper cites The quantization model of neural scaling.

Understanding sparse autoencoder scaling in the presence of feature manifolds The quantization model of neural scaling

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:41:18.666252Z

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 6ce62bc9-b4e6-4086-98bf-8315b461920e · outbound

This paper cites What is a linear representation? what is a multidimensional feature? Trans- former Circuits Thread, July 2024.

Understanding sparse autoencoder scaling in the presence of feature manifolds What is a linear representation? what is a multidimensional feature? Trans- former Circuits Thread, July 2024

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:41:18.650305Z

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 07827292-5c3a-4b18-98f7-2ef6a05ff919 · outbound

This paper cites true features.

Understanding sparse autoencoder scaling in the presence of feature manifolds true features

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:41:18.635342Z

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 701121b1-450c-4f3c-9ea9-5793afdcf8c6 · outbound

This paper cites an unresolved cited work.

Understanding sparse autoencoder scaling in the presence of feature manifolds Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:41:18.620048Z

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 99a2c900-6c53-4f21-9585-adf2225f78ca · outbound

This paper cites Scaling Laws for Neural Language Models.

Understanding sparse autoencoder scaling in the presence of feature manifolds Scaling Laws for Neural Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.971966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69b71016-be2d-407e-9fb8-34ed83a9e1f4 · outbound

This paper cites Training Compute-Optimal Large Language Models.

Understanding sparse autoencoder scaling in the presence of feature manifolds Training Compute-Optimal Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T16:41:17.976234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2c9fdc0-fd90-4a8e-8182-ff875b3fec66 · outbound

This paper cites Up- date on how we train saes.

Understanding sparse autoencoder scaling in the presence of feature manifolds Up- date on how we train saes

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:41:18.605553Z

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 6d873a55-c8c0-4f6c-b36f-35cf5426f2c9 · outbound

This paper cites features.

Understanding sparse autoencoder scaling in the presence of feature manifolds features

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:41:18.590150Z

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.

Pith citing papers

Observation f5efb220-453d-48ba-8e49-7567a34a87ae · inbound

Linear-Readout Floors and Threshold Recovery in Computation in Superposition cites this paper.

Linear-Readout Floors and Threshold Recovery in Computation in Superposition Understanding sparse autoencoder scaling in the presence of feature manifolds

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T17:01:06.053883Z

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 270c6609-5820-4cd9-b09c-fbd89de2caf7 · inbound

Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention cites this paper.

Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention Understanding sparse autoencoder scaling in the presence of feature manifolds

Reference 137

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T08:43:15.189013Z

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 1689f233-0a41-4144-970c-f07f5f3ac96b · inbound

Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability cites this paper.

Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability Understanding sparse autoencoder scaling in the presence of feature manifolds

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-06-28T02:11:29.096042Z

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 bf416963-e3f6-47fc-96b1-b4a64b1ea4f7 · inbound

A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders cites this paper.

A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders Understanding sparse autoencoder scaling in the presence of feature manifolds

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T16:47:09.908843Z

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 a197f7e4-ae30-41d6-968b-d9bb127aa08b · inbound

Critical Percolation as a Synthetic Data Model for Interpretability cites this paper.

Critical Percolation as a Synthetic Data Model for Interpretability Understanding sparse autoencoder scaling in the presence of feature manifolds

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-07-04T03:49:29.547821Z

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.