Paper Citation Record · LEDGER

Disentangling Polysemantic Channels in Convolutional Neural Networks

As of 17 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2504.12939.

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

pith.paper-citation-record.v1
2504.12939 v1

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T12:29:34.141936Z

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

24 of 24 outbound references displayed

verified exact0
verified fuzzy18
unresolved6
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9bc9122c-2d72-452a-91d0-37ab95944ede · outbound

This paper cites On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation.

Disentangling Polysemantic Channels in Convolutional Neural Networks On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:29:34.664511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 685e1138-e4d4-409c-b31f-32f9ae98b4ec · outbound

This paper cites Concept whitening for interpretable image recognition.

Disentangling Polysemantic Channels in Convolutional Neural Networks Concept whitening for interpretable image recognition

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:29:34.646742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 70d894a7-61fe-4e14-a8de-35f7bdd2c906 · outbound

This paper cites ImageNet: A large-scale hierarchical image database.

Disentangling Polysemantic Channels in Convolutional Neural Networks ImageNet: A large-scale hierarchical image database

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:29:34.629228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 28ceea0a-2800-4040-82af-5fa3eecfde19 · outbound

This paper cites Visual and semantic similarity in ImageNet.

Disentangling Polysemantic Channels in Convolutional Neural Networks Visual and semantic similarity in ImageNet

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:29:34.611958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4065f58c-07ed-4119-aac8-016b992e109c · outbound

This paper cites PURE: Turning polysemantic neurons into pure features by identifying rele- vant circuits.

Disentangling Polysemantic Channels in Convolutional Neural Networks PURE: Turning polysemantic neurons into pure features by identifying rele- vant circuits

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:29:34.594765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 31531fe7-ba9b-4948-a15a-b905382e19ba · outbound

This paper cites Toy models of superposition.

Disentangling Polysemantic Channels in Convolutional Neural Networks Toy models of superposition

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:29:34.575950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 68a34062-c96f-482e-9624-3e2e684528bd · outbound

This paper cites Bengio, Aaron Courville, and Pascal Vin- cent.

Disentangling Polysemantic Channels in Convolutional Neural Networks Bengio, Aaron Courville, and Pascal Vin- cent

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:29:34.555654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f9532686-f7c0-40f9-8c4a-c24969bd5c87 · outbound

This paper cites Unlocking feature visualization for deep net- work with magnitude constrained optimization.

Disentangling Polysemantic Channels in Convolutional Neural Networks Unlocking feature visualization for deep net- work with magnitude constrained optimization

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:29:34.538119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 07ccb376-c936-4588-a4bc-8413a996caa0 · outbound

This paper cites Deep residual learning for image recognition.

Disentangling Polysemantic Channels in Convolutional Neural Networks Deep residual learning for image recognition

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:29:34.520041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 51a98665-09a0-451c-8169-6212020005cc · outbound

This paper cites Sparse autoencoders can interpret randomly ini- tialized transformers.

Disentangling Polysemantic Channels in Convolutional Neural Networks Sparse autoencoders can interpret randomly ini- tialized transformers

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T12:29:34.059714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e55e1aa4-8b84-4b79-8d2b-c74a41cb8917 · outbound

This paper cites Sparse autoencoders find highly interpretable features in language models.

Disentangling Polysemantic Channels in Convolutional Neural Networks Sparse autoencoders find highly interpretable features in language models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:29:34.502036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b1df342a-90dd-41fb-8085-949328e082b7 · outbound

This paper cites Cai, James Wexler, Fernanda B.

Disentangling Polysemantic Channels in Convolutional Neural Networks Cai, James Wexler, Fernanda B

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:29:34.484321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ed25ec22-3ad1-4f43-b99f-4a0492856683 · outbound

This paper cites an unresolved cited work.

Disentangling Polysemantic Channels in Convolutional Neural Networks Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T12:29:34.077304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0e8f753-da50-485a-833e-4bd29552a10a · outbound

This paper cites Compositional explanations of neurons.

Disentangling Polysemantic Channels in Convolutional Neural Networks Compositional explanations of neurons

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:29:34.455359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 399c0446-61ab-4605-ae3a-d6d665092e33 · outbound

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

Disentangling Polysemantic Channels in Convolutional Neural Networks Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T12:29:34.088764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f1f9bbd-834e-4bca-9bf0-fdd36f5eb5c5 · outbound

This paper cites Linear Explanations for Individual Neurons.

Disentangling Polysemantic Channels in Convolutional Neural Networks Linear Explanations for Individual Neurons

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T12:29:34.094557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f10d64b-abe1-4f8d-b227-8a906385a2fa · outbound

This paper cites Feature visualization.

Disentangling Polysemantic Channels in Convolutional Neural Networks Feature visualization

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:29:34.436933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 97c48b91-ef1c-4e20-bb1f-e7daa10fa90d · outbound

This paper cites Disentangling neuron representations with concept vectors.

Disentangling Polysemantic Channels in Convolutional Neural Networks Disentangling neuron representations with concept vectors

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:29:34.416112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f2760fae-ac7b-42e6-a916-9f0a3f502597 · outbound

This paper cites Automatic differentiation in PyTorch.

Disentangling Polysemantic Channels in Convolutional Neural Networks Automatic differentiation in PyTorch

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:29:34.396747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5a507f8f-967b-44f5-bff3-5a3cd4c269fa · outbound

This paper cites Sparse Autoencoders Trained on the Same Data Learn Different Features.

Disentangling Polysemantic Channels in Convolutional Neural Networks Sparse Autoencoders Trained on the Same Data Learn Different Features

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T12:29:34.117929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 745bae8c-3e29-49e9-8d20-8e90aadab802 · outbound

This paper cites Towards a fuller understanding of neurons with clustered compositional explanations.

Disentangling Polysemantic Channels in Convolutional Neural Networks Towards a fuller understanding of neurons with clustered compositional explanations

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:29:34.378699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 68bc6bdf-e296-4d65-9f49-44d57fb7a6b5 · outbound

This paper cites Learning important features through propagating activation differences.

Disentangling Polysemantic Channels in Convolutional Neural Networks Learning important features through propagating activation differences

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:29:34.359952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2a706954-7cef-4d2a-b50a-788376a46795 · outbound

This paper cites Axiomatic attribution for deep networks.

Disentangling Polysemantic Channels in Convolutional Neural Networks Axiomatic attribution for deep networks

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:29:34.337586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 11c5b09b-adb1-4bb7-8871-25e75ff5c78f · outbound

This paper cites AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders.

Disentangling Polysemantic Channels in Convolutional Neural Networks AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T12:29:34.141936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.