Paper Citation Record · LEDGER

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models

As of 9 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 3 inbound Pith citation observations for arXiv:2506.07406.

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

pith.paper-citation-record.v1
2506.07406 v3

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:44:34.878071Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T22:20:52.947124Z

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

24 of 24 outbound references displayed

verified exact0
verified fuzzy6
unresolved17
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

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

Outbound references

Observation 7de31c2a-3748-41af-83e5-97b57e0084c2 · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T05:44:34.811248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 884b5900-8b90-48f0-9d6c-44d7f2449931 · outbound

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

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T05:44:34.824559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e292e361-3379-4728-9338-230cabb9bbb4 · outbound

This paper cites In-Context Learning Creates Task Vectors.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models In-Context Learning Creates Task Vectors

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T05:44:34.837497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e71ec9b-eeab-4355-9b5f-4fca8bccb89f · outbound

This paper cites RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations

Reference 10

Resolution: malformed identifier; no resolver link, observed 2026-08-07T05:44:34.840406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99ca24ad-20bb-4290-94dc-230070a0d686 · outbound

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

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T05:44:34.843022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96bf3527-f6c5-476c-89b8-a478013b0911 · outbound

This paper cites Understanding deep image representations by inverting them.2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Understanding deep image representations by inverting them.2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:44:35.102039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7465a8b7-834b-4ccf-a356-ba4da15f6817 · outbound

This paper cites Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T05:44:34.851804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f4976f0-6dab-4d11-b9ec-2840a7e3155b · outbound

This paper cites The Linear Representation Hypothesis and the Geometry of Large Language Models.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T05:44:34.857742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a525b8f-a385-4852-9f8b-4e0c8b325bc5 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Gemma 2: Improving Open Language Models at a Practical Size

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T05:44:34.862975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f3ca20a-8fa8-4ff4-817c-02d1df676dd5 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T05:44:34.865749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2b18c6f-035b-4e61-bfb7-531a1aa1829f · outbound

This paper cites Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T05:44:34.868186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 841875b3-b3fd-4295-abc1-cd2f2616e098 · outbound

This paper cites the indirect object name in the prompt.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models the indirect object name in the prompt

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:44:35.094101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b2bb17f5-66e4-40da-9e8f-24620bb3cd3e · outbound

This paper cites Training is performed for 100,000 steps with a batch size of 2048 using the AdamW optimizer.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Training is performed for 100,000 steps with a batch size of 2048 using the AdamW optimizer

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:44:35.078733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2e9583d3-d141-45cc-a038-8bc837b5cbc8 · outbound

This paper cites [City] is a city in the country of.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models [City] is a city in the country of

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:44:35.069695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 767522fa-2384-4c3c-9976-8dde24a8ac93 · outbound

This paper cites Then, [B] and [A] went to the [PLACE]. [B] gave a [OBJECT] to.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Then, [B] and [A] went to the [PLACE]. [B] gave a [OBJECT] to

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:44:35.086347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 46645982-f0df-4415-955e-f13c988cb566 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Scaling and evaluating sparse autoencoders

Reference 2009

Resolution: unresolved; no resolver link, observed 2026-08-07T05:44:34.827442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54d2460e-b0c6-4b0b-a2e0-f976a85526ea · outbound

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

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Mechanistic Interpretability for AI Safety -- A Review

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-07T05:44:34.814735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 441ed5b6-b3e9-411b-81aa-d2ea158f8d60 · outbound

This paper cites Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-07T05:44:34.849126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cc61af8-21d7-4fe6-abc9-ff6dbf5e32d0 · outbound

This paper cites Alexander Pan, Lijie Chen, and Jacob Steinhardt.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Alexander Pan, Lijie Chen, and Jacob Steinhardt

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-07T05:44:34.854358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47020588-307b-4faa-a301-657d98bd9649 · outbound

This paper cites Open Problems in Mechanistic Interpretability.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Open Problems in Mechanistic Interpretability

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-07T05:44:34.860460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 989dcab7-d626-48ea-9f7b-930feae4c211 · outbound

This paper cites SelfIE: Self-Interpretation of Large Language Model Embeddings.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models SelfIE: Self-Interpretation of Large Language Model Embeddings

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-07T05:44:34.821849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15a5bb06-6583-43b2-9dbb-38e809088d8f · outbound

This paper cites Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T05:44:34.834001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 905a8033-9350-41ff-9817-2c76ad7eb2e4 · outbound

This paper cites Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:44:35.110407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2a069249-8b0a-4bd1-96b1-37b4a6ef079c · outbound

This paper cites Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T05:44:34.830593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation fb51bfd6-9f2e-41b7-b344-ebd22b0de95f · inbound

Rep2Text: Decoding Full Text from a Single LLM Token Representation cites this paper.

Rep2Text: Decoding Full Text from a Single LLM Token Representation InverseScope: Scalable Activation Inversion for Interpreting Large Language Models

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-07T03:18:08.538842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6fc72081-ca3a-4f5c-bb10-c4f8d34b83fb · inbound

Mechanistic Interpretability of Cognitive Complexity in LLMs via Linear Probing using Bloom's Taxonomy cites this paper.

Mechanistic Interpretability of Cognitive Complexity in LLMs via Linear Probing using Bloom's Taxonomy InverseScope: Scalable Activation Inversion for Interpreting Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T22:20:52.947124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d512d461-2c4e-43ce-bc65-3833159c71c0 · inbound

PRISM: Recovering Instruction Sets from Language Model Activations cites this paper.

PRISM: Recovering Instruction Sets from Language Model Activations InverseScope: Scalable Activation Inversion for Interpreting Large Language Models

Reference 36

Resolution: metadata mismatch; arxiv_id, observed 2026-07-07T03:18:08.538842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.