Pith. sign in

Paper Citation Record · LEDGER

Do Sparse Autoencoders Identify Reasoning Features in Language Models?

As of 11 August 2026, this Paper Citation Record lists 100 of 120 outbound references and 1 inbound Pith citation observation for arXiv:2601.05679.

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

pith.paper-citation-record.v1
2601.05679 v7

Coverage vector

measured 100 of 120 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-21T15:52:27.900929Z

measured 101 of 101 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T16:08:01.995919Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

100 of 120 outbound references displayed

  • verified exact0
  • verified fuzzy99
  • unresolved1
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 198003f0-d1e1-47f6-8d20-7df3a1dfa6f4 · outbound

This paper cites Then, you will cross the river using the old bridge.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Then, you will cross the river using the old bridge

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.460710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:1e469aaedd9182098da043629455b7437b64067190ab0d5d6d95bb97c9d0fd34

Observation 7b30e31b-f48c-426c-b269-cc259a83794c · outbound

This paper cites Then, you must traverse the glacier efficiently to avoid the risk of falling.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Then, you must traverse the glacier efficiently to avoid the risk of falling

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.354210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:4b35c5e05761d215bbf1f5e76d0ea968547d27e89c54fa7cd51adc1b685d27c7

Observation c344a49a-a975-414d-87db-558d1304fc0d · outbound

This paper cites The legal department should then review the consent forms thoroug.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? The legal department should then review the consent forms thoroug

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.352406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:836a92b6010ebe78a0564999d8d1a0f86cc8806e049e4b7469f26f8a9f394d23

Observation b871e866-d07f-4a0b-a5ce-fbe0190b24e3 · outbound

This paper cites Traditional systems compress images into fixed vectors, causin.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Traditional systems compress images into fixed vectors, causin

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.375561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:f8694be693ae6e201034e87b911a477496ab75440e8ce78859ac993ca3072d3b

Observation 123cab18-b1ba-4738-a479-1a75df4493f4 · outbound

This paper cites Humor relies on complex human traits missing in current software.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Humor relies on complex human traits missing in current software

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.346023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:f50b3fab4b77c2c3e7dabd01b58b8812e2b969741909e2b1a521706174362163

Observation e7dea8e4-3dd0-4e5b-be95-9272e749cef5 · outbound

This paper cites separately.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? separately

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.405651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:71b7c9f824e427e6769549c2e3a83dfb0b0d2a6aa9755638c7dae5d0c651e961

Observation e8441bc3-5424-471d-afb8-0805f2e41ace · outbound

This paper cites First, I’ll cushion the cups individually with paper.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, I’ll cushion the cups individually with paper

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.388145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:b1f0cf9ba8acd4e225f441d04736104747e4251ac834ce953cf83017052d86cc

Observation 664c1295-e7ed-45c8-86af-e577a2789b76 · outbound

This paper cites First, I’ll spray the strands individually for hold.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, I’ll spray the strands individually for hold

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.382967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:cd097db9b6dcf84e347a4c56668f9395c5d2e889f49ef3d6a1e043e645b2332a

Observation bff4e375-e416-4860-beb7-5e8937041943 · outbound

This paper cites First, I’ll spray the cuffs individually with starch.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, I’ll spray the cuffs individually with starch

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.462429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:35e2d8a0120e340035d7db75a68e09b7284adab959eec07b37374e28091ce218

Observation e030580e-a381-41f4-ac83-a1463ee925c4 · outbound

This paper cites Spotting these challenges helps us find targeted solutions for keeping syste.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Spotting these challenges helps us find targeted solutions for keeping syste

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.321031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:f840b7e0e91164f499a5d95d7597b56d1a26dcb15596ab28ee67854b00678af1

Observation 94f4e371-ecbf-42e9-a59e-5db6c26d650b · outbound

This paper cites This strategy gives us the total duration by combining the two parts.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? This strategy gives us the total duration by combining the two parts

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.329769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:a58b5d904c4db80f7a32a6d5b40e9f2d1a5ca60d534aab0b6c041138879ceb7d

Observation 1cec637e-f65b-47c8-8323-eb34612f738d · outbound

This paper cites effectively.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? effectively

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.279548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:85b39506f25d9563e5e9634d031e78e747710ea83f745e9d0f678846711a37dc

Observation 8502af5e-f581-4a9a-bc5d-b8635c32deb8 · outbound

This paper cites Next, I thoroughly inspected the storage tanks.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Next, I thoroughly inspected the storage tanks

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.283697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:c54bbbb9739cc031017cffc5f909b3653e73787a9c33537a8078ea883f410c5b

Observation 4a81ed7e-55df-48f9-a22e-8f187b8f8474 · outbound

This paper cites Next, I thoroughly labeled the cables.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Next, I thoroughly labeled the cables

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.272044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:7b48862b05c7ae423925eb5f187c1f21804d43bf9daedb8ed65eb5cd9f5ad6e6

Observation 10304ce4-f3c9-44ff-beaf-cc1840a8acae · outbound

This paper cites Next, I thoroughly organized the tangled power cables beneath the shared workstations.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Next, I thoroughly organized the tangled power cables beneath the shared workstations

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.355993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:f45a6152728bc1f1179f559930d92bb9fb67507b3cda4c3fdba0fea3a8f94d32

Observation 503b25ee-9e08-4b1c-816c-8c4bd84b3da6 · outbound

This paper cites Jane starts with 7 and gives away 4.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Jane starts with 7 and gives away 4

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.351890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:e9fd7e64fca44fb9850fadf130a95eebd2c1cc12e85de3a0e45f1987b60d7ad2

Observation 9c085b7e-37e3-44ac-a5d2-784d8f1f08ed · outbound

This paper cites Recent developments have seen models producing high-quality images and text, marking a significant shift in the capab.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Recent developments have seen models producing high-quality images and text, marking a significant shift in the capab

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.329071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:51d9a73a4862cf4144c36530983cbe71988b1d0cac4972e365fddc11a8fb1f42

Observation 964a360a-90e4-4136-a92e-b47507144e4f · outbound

This paper cites I”, “My”) with sequencing markers (“First.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? I”, “My”) with sequencing markers (“First

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.371575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:cec36d88893c6602eea244e31f6078a4a9067129271e7134a05f9c767d1a274d

Observation fd58da2a-a6b8-4eaf-95bd-7a8f2a85fcf8 · outbound

This paper cites First, I need to define the user inputs.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, I need to define the user inputs

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.327183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:eb59f375b1f4ba921b3fe2420eb746fe864163a30fe9f98abea9311517a0657e

Observation 1f944811-8bb7-4257-8f29-2f61f8622105 · outbound

This paper cites First, I need to identify the author’s objectives.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, I need to identify the author’s objectives

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.391845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:345afed1040440d086c630d7cea7b5e44e173cc9238561187149169ef3fdcc9d

Observation 16bc4c98-4364-4ac7-a69c-3956613056f7 · outbound

This paper cites First, I need to consider the narrative explanation.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, I need to consider the narrative explanation

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.390128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:bf251782754e7ca3dd42d846f46ae5e5e8e9dca4e01a944c29d278b1f37f8faf

Observation db5cbcc1-7fa7-49cd-86f7-976865e60f8c · outbound

This paper cites It essentially measures how well a model performs tasks like classification.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? It essentially measures how well a model performs tasks like classification

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.393606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:6ce780e8f09e6bad2ea91724d00fac59197dbe1dd7f6e7585cbf6a83c1c75ad0

Observation d355f98b-5529-4df2-82e0-816fa8f286ee · outbound

This paper cites To provide a comprehensive answer, one must examine the various phases of the writing process.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? To provide a comprehensive answer, one must examine the various phases of the writing process

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.305112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:68429d6dad7ea5a88a2ffe7f25c73d6c8f2a55278ccdf3cfeed3f98885615a31

Observation 44a321fe-6db6-4d42-b4b1-91c1605f0cd3 · outbound

This paper cites Indexing is a critical tool for faster data retrieval.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Indexing is a critical tool for faster data retrieval

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.395439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:8b12600f33c792f1ade9a2827bdeeb71e373cc3f1286e940faef2b5c5a9625ca

Observation a7f55e1d-2cd2-401d-81c5-62720824b977 · outbound

This paper cites I should look for the pre-drilled holes near the edge.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? I should look for the pre-drilled holes near the edge

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.317504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:9f03e47716e37e0b7074f1ff361bddcfa1fec670b5d25563f4e769dfa27463a9

Observation 73d4ae8c-89e0-40b1-b42b-815468a13dd0 · outbound

This paper cites I should look for the recommended pressure on the door label.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? I should look for the recommended pressure on the door label

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.319562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:aa4c429fed8d8f03a8aa8220ef48638ac9d225ba65263417180c5a4ebfaec10b

Observation 19d09703-19fc-4c34-8b45-2d28c1562df4 · outbound

This paper cites I should check the time on my phone.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? I should check the time on my phone

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.325159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:5a84bab5e2153466c9f368f9ba19df275f8c7f450c820c2b956aa10acb6fd944

Observation 0171302f-8b42-46bb-a254-72b7fb43e82c · outbound

This paper cites The situation calls for integer division.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? The situation calls for integer division

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.330850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:3a6c0da0eb0722e818b89dea770a0ee95b0965fecf06a0e12bc188e2b62f7196

Observation 42acb83c-0e64-4096-829e-2569274e5d1a · outbound

This paper cites Mike holds 4 erasers total.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Mike holds 4 erasers total

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.341936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:b4e72ffdc0d7ea89e488df340055148705a3452c77bb59bda58650f16733cfae

Observation 6bcfdb41-5461-48a1-8718-17645e98ef07 · outbound

This paper cites With 4 bananas and 2 buddies, division is the necessary operation.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? With 4 bananas and 2 buddies, division is the necessary operation

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.340013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:1926553c7e33cf6e131e219b4fd4df44cb5ba2d00f25dfe7f427afb4adbbc609

Observation 539385e4-035f-4195-8983-5eb1338348f6 · outbound

This paper cites First, I need to recall the secret message.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, I need to recall the secret message

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.347816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:66677ac95db7c4d4e840b625d902ababeeb16e2ee75b15f6cf30ca574d03ccd9

Observation 9c52703f-2d11-46a2-b3b4-e8c3bc547b21 · outbound

This paper cites First, I should outline a color-coding system.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, I should outline a color-coding system

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.307556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:dbc73692a578077718e87a7406d1eed09932766d49209b0f2d9f4e09290dfbbf

Observation 390b18cb-bc38-46b9-a8ba-d158c90a9814 · outbound

This paper cites First, I need to identify the type of tea leaves.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, I need to identify the type of tea leaves

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.314513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:e85516967090b4d7c741df43c5effbb1784d1862dc207d9337bbac06b1b26eac

Observation 8fc6190a-fd63-4515-8e14-407dd94312df · outbound

This paper cites The code itself must change to accommodate the structural differences between language.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? The code itself must change to accommodate the structural differences between language

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.311672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:6cb8af51e844704e59c1a9f0044316138e6920569df88e4528ac3fd224213d6a

Observation 56d89344-f1f1-4c49-ad25-24a873ea5388 · outbound

This paper cites an unresolved cited work.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Unresolved cited work

Reference 35

Resolution
unresolved
raw_fallback, observed 2026-05-21T15:54:15.333770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:9150c042a818a1d5cf6b35eef887b4d3fe79ae38677022ff84be71046b768713

Observation 1e90887c-568e-45f5-a879-65ae10fbbe24 · outbound

This paper cites limited resources and time.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? limited resources and time

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.239202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:ec19d9d6c200f1d14a4a58c00d2543bdc60d13db27e867847f23e20cfd927777

Observation 953dc790-456e-49cb-86a2-f61cc2b9d9a1 · outbound

This paper cites First, I need to sift the dry ingredients into a large bowl.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, I need to sift the dry ingredients into a large bowl

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.247017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:4e4bcf3a0fa904d8d5c8011bdcbc83fd8458e9f0feaf8144d3f638887fbd783a

Observation bfcc7848-ec69-43ff-b7b4-3ee4bde4ed5a · outbound

This paper cites To stay alive, I need to reach the ventilation shaft in the ceiling.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? To stay alive, I need to reach the ventilation shaft in the ceiling

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.260067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:bfe137b1091e313bb7846fbbac3eae231e506e40e7aad7fbb26bd8d7bf1ed385

Observation 73517053-4f3c-4d9f-8260-663c26c56eef · outbound

This paper cites First, I need to lay out all the wooden panels on the floor.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, I need to lay out all the wooden panels on the floor

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.327961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:e2c07635470c3b998461283b413b6316983c554009a4463d56c228aaba4328d0

Observation b97ac417-cdae-48f3-8b84-cd77ba28f2a5 · outbound

This paper cites Prioritizing strategies that maximize impact while minimizing effort is key.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Prioritizing strategies that maximize impact while minimizing effort is key

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.464260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:3287cea7aaf553407cbfb071ae39fb9bbb5766c9b324ab1381c9b5872a65c4ab

Observation 6ecc0322-8bdc-43f7-85dd-0e88127b2172 · outbound

This paper cites Breaking figures into hundreds, tens, and ones seems optimal, facilitating tracking and mirroring standard learning.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Breaking figures into hundreds, tens, and ones seems optimal, facilitating tracking and mirroring standard learning

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.469509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:0e1dcc4df502a5aea90555d7c4587f0ff897ae77c9b667f710585a2a4ceb9993

Observation 89000fdb-6ba2-44e0-835f-669f19ae1c36 · outbound

This paper cites What are the different types of AI?.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? What are the different types of AI?

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.471202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:5c9ad67c6b3b65af38e7e5a26232d022f28f638bcbb7f1bd50c18a49aa3a7890

Observation 27e2c624-fbf8-4d46-8f15-37e99f36ef71 · outbound

This paper cites First, I should define the nature of the fog surrounding me.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, I should define the nature of the fog surrounding me

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.449898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:b9e2e1ff50a4be8d1ad46c6b098c369db5aa44a7dfc44236b7756bb7762f930e

Observation 51d57a69-aab5-4cdc-9fe9-a256fd22c7fe · outbound

This paper cites First, I should define the mood of the room to avoid tension.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, I should define the mood of the room to avoid tension

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.451526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:0aa715701ce580b04800b244a005674b832cbf15c79680c7b42b6b7e73723c06

Observation 5f62a6fb-2e81-40c5-9de0-481ea5074148 · outbound

This paper cites First, I should define the posture of the central figure.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, I should define the posture of the central figure

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.442360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:b3e0dd62526d75fd1cd5f385a4b1300bbcf7e7d8ce08c574361f010e00a664c1

Observation 93ead820-3cd1-4390-8990-5cba7c79ad4f · outbound

This paper cites Step one is grasping the essence of subtraction and how it ties to addition.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Step one is grasping the essence of subtraction and how it ties to addition

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.440324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:9641a3278ea1ad7fe3bcf3bf6f403f23cd81eea38cadf8824cee5b7db5e89b79

Observation 87391e68-0552-43eb-a8a6-bf7e7698deb4 · outbound

This paper cites A solid response involves exploring NLP’s role in daily tech and business.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? A solid response involves exploring NLP’s role in daily tech and business

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.444250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:a1cb777439fb37237be8ff6bda817b8a4145d9caf52360862582872647f6af7d

Observation 41f83bc4-3221-483e-81a3-dc72625325da · outbound

This paper cites break down.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? break down

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.436160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:c57c2d17d2cc333adc4da552c06a5e65fce48c8018b3d39cb90d0f932410125d

Observation 72cbb986-2330-4a3f-b2b6-3898fe225be7 · outbound

This paper cites We have categorized the settings menu to break down complex options into distinct panels.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? We have categorized the settings menu to break down complex options into distinct panels

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.434035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:ad4505d651e7bd9478d3c6a942d3708352b8bbfa19150b999bf2312a397481a3

Observation 8981029d-73f8-4b6f-a4a1-032517bd2c1f · outbound

This paper cites It categorizes the potential risks to break down the emergency protocols into distinct action plans, focusing on empl.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? It categorizes the potential risks to break down the emergency protocols into distinct action plans, focusing on empl

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.438068Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:bf440fc0a5d807b3224e6c5e9ece633ef4707c811741852888386b573322335d

Observation 1620dbd2-b927-4d8a-91d0-4c552c62c7aa · outbound

This paper cites It carefully categorizes the transaction logs to break down the complex revenue s.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? It carefully categorizes the transaction logs to break down the complex revenue s

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.446323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:689d003385082004bc5a6cb96e5ae07fc2a2c5a2e51bce3e58fee1844de12dd3

Observation 7cdd1b3d-c938-4a68-b770-7de369d48a9a · outbound

This paper cites It starts with realizing that this involves more than just translating words.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? It starts with realizing that this involves more than just translating words

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.427845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:728007521654d017510b14e6d623991d1f557a7a381539a0311ade57469e9815

Observation 065b13ea-5b69-4e0d-8e0a-a7a1f727b153 · outbound

This paper cites It starts with realizing that this is more than just translating text.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? It starts with realizing that this is more than just translating text

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.425948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:166a54f008d16a6eb63607aebf546273f01193a471b518ea6af539d1dac2c084

Observation da548d2a-aa7e-486d-8b84-0e85b6f5594d · outbound

This paper cites I” when used in the context of meta-cognitive planning, self-narration, or outlining a response strategy (e.g., “I need to.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? I” when used in the context of meta-cognitive planning, self-narration, or outlining a response strategy (e.g., “I need to

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.430135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:8abd5f008521826c6c7d7a2944b266fb1ced1994d8dcd650578f7b4485f88273

Observation b1d160ee-71bd-40a5-9903-68f90198f58d · outbound

This paper cites First, I should consider the introductory module.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, I should consider the introductory module

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.422513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:e1aeee86b1017c1a07dd6dc7678fd6c50f200e687b63d4426b86ec4859706faa

Observation a9ef910f-f118-49a3-bacb-9e9c3d35c0c4 · outbound

This paper cites First, I should consider the activity of the wild yeast.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, I should consider the activity of the wild yeast

Reference 56

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.420807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:33091a93155b8c8d7dec1e5b14939a88959ecb9ff4725c01cc85e0fd1d96e7cc

Observation 73f16a7d-4603-4c0b-91af-a99838aaa66c · outbound

This paper cites First, I should consider the layout and flow of the room.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, I should consider the layout and flow of the room

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.424128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:8be2425780cd2f7fbab98045eb954a1070b93223938c360ffdfdd545bf6ecc36

Observation eb458f56-9bf8-4bf6-b0af-b5445bddf9b6 · outbound

This paper cites Indexing functions as a primary consideration.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Indexing functions as a primary consideration

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.432053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:63fc9c9da0c19648446db635e1f14594f1514f8e7b293ffc1b1339cf328603c8

Observation 9f6967de-6825-48c3-a941-10eaec7960d1 · outbound

This paper cites The definition should characterize estimation as a method.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? The definition should characterize estimation as a method

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.448081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:57a6b528ec0be7284889f1439d243174b867494e24efd33ff124e7aaa18b1f4b

Observation 157942bb-b62d-4874-89a0-904b4690e342 · outbound

This paper cites First” or “To answer.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First” or “To answer

Reference 60

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.455265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:6dae251810145ef0feb14f1f3a8c4f606a4bbcd23c1813d6ab389f64b24a8765

Observation a37d48a6-06a9-434c-b515-c646524b504d · outbound

This paper cites First, I need to identify where the carrot nose went, as this is the most pressing mystery of the.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, I need to identify where the carrot nose went, as this is the most pressing mystery of the

Reference 61

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.410062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:b98f2a848bea11aa87d2db574100808b58a9dddb53dbdd8a5b6b3c125ee7dea8

Observation 601140e4-36ec-4f3a-8e8e-cf78b855f801 · outbound

This paper cites To compose this symphony, I need to consider the rhythm of the city streets and how the traffic sounds blend into a chaotic harmony.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? To compose this symphony, I need to consider the rhythm of the city streets and how the traffic sounds blend into a chaotic harmony

Reference 62

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.411851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:a457cc9555ac4d342b219d2096b3ec57656f556d69f8c570b3ee83ef984fe3ee

Observation c4dfd22a-ab1b-40c0-ab7e-ab11e248b138 · outbound

This paper cites I should identify the color of my wings and determine if I can fly towards.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? I should identify the color of my wings and determine if I can fly towards

Reference 63

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.402294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:4f54e66c33aacda2f7cd90fd376371c795bc709862092a0e7f417e3b089d041f

Observation bf29b1eb-88fe-4e1f-a71c-4a4eb943f9d1 · outbound

This paper cites Usually this implies handling regulated or confidential data.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Usually this implies handling regulated or confidential data

Reference 64

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.404312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:6ac035917e0efd7f9d8c21dba003d1babf39eaef2ea0ae84b83329b8659705bc

Observation 27f43c60-0575-4108-a9d8-0f1607f2542a · outbound

This paper cites Next comes accounting for the 2 additional marbles she discovered later.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Next comes accounting for the 2 additional marbles she discovered later

Reference 65

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.398525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:5f4ce88a302a569b31798589ac9b3a66b7372af79ca3ff6d52ad4ccc0dccae1b

Observation c76f54c8-0387-4abe-9798-35ca765ed358 · outbound

This paper cites process.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? process

Reference 66

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.396494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:7073cccb7efcc707cdec750b30ab1244b2227fdf9d2fe5d667d23af475e52f0c

Observation a913819d-2636-48bb-b2a4-503646768111 · outbound

This paper cites She noted that the **structure** was awkward and the **topic** was unclear.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? She noted that the **structure** was awkward and the **topic** was unclear

Reference 67

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.400504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:70606f51de9e84cd5d8d2a6809772e11e298a56527e4cfe4d62f15aab1dea735

Observation 0cc8f7fd-50cc-41b6-b4ad-b8d2625a0a77 · outbound

This paper cites It describes the **functionality** of each **element**.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? It describes the **functionality** of each **element**

Reference 68

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.406252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:a2e1d34c5ec2aecdfd5831b096eed9c048782ab2e4f07f896ecce748c0c0a2a2

Observation e9372834-5c80-4780-add6-37c93db8c686 · outbound

This paper cites The **topic** of discussion was renewable energy.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? The **topic** of discussion was renewable energy

Reference 69

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.408070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:3e53f4c8d8e295e3788c9ddac94790edcb9fe37c5f1ff878f6a0e88015f63be7

Observation 1e4658b5-3687-46fb-b307-f9a03cb87021 · outbound

This paper cites I’ll look at clarity and engagement.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? I’ll look at clarity and engagement

Reference 70

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.387918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:26501fa6bede90259247b6da7f260a9ba582e68ef383e1c192aa32ae406e4c44

Observation fde46f6f-11ee-4344-be24-a48901631f82 · outbound

This paper cites Because of the zeros, I need to borrow.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Because of the zeros, I need to borrow

Reference 71

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.390412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:502ff3d08dee6f5c979cc6330818b012e5e834eca543064a78b3dd8144aded51

Observation d82a1624-0d99-4a12-a035-59c222316177 · outbound

This paper cites the”, “its.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? the”, “its

Reference 72

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.394446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:811067109afbd5c892b386fcd870813d8ae1945e5f2ec26c634de2429181c73d

Observation 2ceb4be3-4a97-4417-863f-d13fb7f1a99f · outbound

This paper cites // The entire script relies on this file.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? // The entire script relies on this file

Reference 73

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.381099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:0579076134ae0e4bd90a56aadce51a95745c6eb38a7f87f50226c1a7692fb9e3

Observation e60c2c4e-9293-4611-8eea-5f643ac39cab · outbound

This paper cites To see the colors, I use my binoculars.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? To see the colors, I use my binoculars

Reference 74

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.382752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:c0002d77d344980813c2735c7ef3cbb696d56c97e87ef73ed53341017adab20b

Observation c37ef51c-24c4-4172-8d50-dbefde489156 · outbound

This paper cites // The entire process runs in the background.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? // The entire process runs in the background

Reference 75

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.379368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:0c26f66b0d5ab47f6d7cf399ee557c9fb3c1c41e8bdf3e31244902722bbb49ef

Observation 1beeb686-9d76-4129-a364-363a65db1b79 · outbound

This paper cites Typically, such requests involve multiple tables, intricate filtering, plus massive datasets.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Typically, such requests involve multiple tables, intricate filtering, plus massive datasets

Reference 76

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.384948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:f3cbd91d872ff8a1b612418e90cc0550502c9f1e7937bdf803c878cea4ca1686

Observation 9859b3f1-7849-4f3b-b726-31283350b6c2 · outbound

This paper cites First, introducing`sorted()`functions and`list.sort()`methods is best, noti.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, introducing`sorted()`functions and`list.sort()`methods is best, noti

Reference 77

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.392543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:64aa9838212caf56c75d9b905dc09b80544545809187edb81229a844f33f3e35

Observation 6f8b2733-6187-4ab7-81df-0ac7e19acea5 · outbound

This paper cites First, I need to.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, I need to

Reference 78

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.413559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:e530c1c60a5709e5693f4b9c17ae0f169700ef2c782f3ec94285f207552a1ef9

Observation 1cfb81ac-acc0-4491-a261-ec6a2e9050ed · outbound

This paper cites It is hard and inedible, so I use a small paring knife to carefully cut it out.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? It is hard and inedible, so I use a small paring knife to carefully cut it out

Reference 79

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.415284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:4bd6cc9275c8a7bd8fc59b42aa15e59ff4a2461b60a07541927018cf37e64b50

Observation e7924678-0a0e-4b96-a558-982e6b19e728 · outbound

This paper cites There are so many black bags that look exactly alike, circling around and around.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? There are so many black bags that look exactly alike, circling around and around

Reference 80

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.457107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:35214c3e0cacecbec21f6178ab8bb034796ed6f37e973f2d09209e5f2eec4c58

Observation da9f050d-0280-4bac-92c4-b4cfba5bc584 · outbound

This paper cites I ran all the way from the subway station to the office building because I overslept and was running late.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? I ran all the way from the subway station to the office building because I overslept and was running late

Reference 81

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.371709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:0240761bd979ab85f0e4846e034f4a52744aa680dbb5cf36ca21f5f64aa673da

Observation 9b9f403f-7ee1-48ec-b287-8628e3e89947 · outbound

This paper cites These elements typically comprise machine learning, natural language processing, and robotics.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? These elements typically comprise machine learning, natural language processing, and robotics

Reference 82

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.475218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:d0d898445033550887087c030e10254c7b710ef7bed7b6fe1152fd4fe37a2d6f

Observation 26937fcc-a322-4768-9d05-8be3f91725e3 · outbound

This paper cites To handle this, breaking down the concept of accuracy is required, along with finding methods that influence it.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? To handle this, breaking down the concept of accuracy is required, along with finding methods that influence it

Reference 83

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.368037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:51bc6b26ab5110ac48da19a9e6428f564b1754198f66de3e74eddb46280ba9d7

Observation de703386-9d38-44c4-bc43-8825e195bce5 · outbound

This paper cites limited resources and time.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? limited resources and time

Reference 84

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.369763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:e525955ce26e5b96b56980ac3872d919a72816f8897d0f0fd0b708b3eca2e507

Observation 14c53d39-830a-47ac-a447-d491f545f9a8 · outbound

This paper cites You simply need to let me know the time.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? You simply need to let me know the time

Reference 85

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.373688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:68a2b4616670adbc2cbc56ff0772d7b4e40a56a3a75ea9a96f85b6f5a04cf466

Observation ff808861-9a96-43ea-8f7c-97d1f5d99c98 · outbound

This paper cites This allows me to lift the lid.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? This allows me to lift the lid

Reference 86

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.361641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:279da383bd89049be890ba4c67dbf1b42ca576b4dae8c76ccf51397656f35f1e

Observation 4e8081ba-91ed-4ba9-bff5-9f93ad442029 · outbound

This paper cites It leads me to feel guilty.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? It leads me to feel guilty

Reference 87

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.363942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:4c9aaba91db975af089fabe28e401071165036131f1a7aefefd53aeb56834dd5

Observation 1073e90d-d3c8-46f3-b842-0c4bd3fd509b · outbound

This paper cites This requires prioritizing high-impact strategies with minimal time or effort.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? This requires prioritizing high-impact strategies with minimal time or effort

Reference 88

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.357934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:bb54f2d11cce7a3f2491407b47e516b2198da37ef8cf47440c906bfec6c3aa78

Observation ff181564-529a-4c58-9fe0-c48883e4cdc1 · outbound

This paper cites Defining the core principle comes first: subtracting a negative equals adding a positive.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Defining the core principle comes first: subtracting a negative equals adding a positive

Reference 89

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.359769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:8936a3c7922b74f7fc8a3cc63d4a85c3e335b9500ec3cd778c0868e25466b4c3

Observation 981bb80d-f59f-4869-83be-2a0285f8e297 · outbound

This paper cites Then”, “Next.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Then”, “Next

Reference 90

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.337336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:2c2207632fb600b97d87e230085f8a9464ef00d0c812007b5f55647040e171c8

Observation 1f845a2d-da6a-4866-8df6-4f2b44d0dfdb · outbound

This paper cites Initially, the color looked too dark.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Initially, the color looked too dark

Reference 91

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.335450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:a6e428718d1d396a93925a10c833e4ec4fecb6f10f1f0d5111b1b301c372ed91

Observation e9535b88-5e8d-4f1f-9bb4-6f39a8c1f454 · outbound

This paper cites Initially, the dust made me sneeze.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Initially, the dust made me sneeze

Reference 92

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.340273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:ba39ec433b807dd87e8ff220815c18d93939352846fa7de7860e1d59858a5555

Observation 155e8e3c-3caa-4cf1-be1a-7a6156ebe6ce · outbound

This paper cites Initially, the parts looked similar.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Initially, the parts looked similar

Reference 93

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.344041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:ec785f4706469d196d413af1dbcde1011c5e662c8c28ce20dc956f79752098dc

Observation e19d0e74-0047-4b65-8687-57a7831591b6 · outbound

This paper cites Seven times eight translates to adding the number seven eight separate times.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Seven times eight translates to adding the number seven eight separate times

Reference 94

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.350423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:e7d3ac0cb2088c4b60616e176ecaf77f371662774fee67454144e891d15cc31d

Observation 06916509-8045-47cc-97d6-a50652c9a7e6 · outbound

This paper cites The market sales accounted for two-fifths of the 150 total apples.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? The market sales accounted for two-fifths of the 150 total apples

Reference 95

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.356171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:b177a2ae6bfb7fe43925350b154c878c3f681dd7a4f4cac3a2c4f77ad67cf66b

Observation a37c1119-57f5-4927-bf39-c4be2475a500 · outbound

This paper cites First, I need to.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? First, I need to

Reference 96

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.473353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:76cdcc71196a0fdfad78a36fc12ed39f384c9965be9ded120418f085c22d3382

Observation 71b92045-3d5f-42e5-80e2-773675133fa7 · outbound

This paper cites The key is right here in my pocket.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? The key is right here in my pocket

Reference 97

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.373494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:2c0424163805bc094c071f47227d49bfcbe04130c936bfddb744239d4e6ceb4b

Observation af39ed7d-b5f2-4941-910d-5439f5f459e8 · outbound

This paper cites It is covered in crumbs from dinner.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? It is covered in crumbs from dinner

Reference 98

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.399760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:472f1448d79121e462eb9f0fb14c3bfd9932d78e4a66cfc73f6fa56779a4e9da

Observation b10f011b-6991-4446-b80e-4c13ad6d2cf8 · outbound

This paper cites It is freezing outside today.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? It is freezing outside today

Reference 99

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.357576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:d7da716efce405529b4bbc8ed61a0abc1e5768658768a9ad79ad5822658f58c6

Observation 54fb955a-8d55-4b18-8cf6-9b583a3eb308 · outbound

This paper cites Add the 2 extra marbles she found to that amount for the total.

Do Sparse Autoencoders Identify Reasoning Features in Language Models? Add the 2 extra marbles she found to that amount for the total

Reference 100

Resolution
verified fuzzy
raw_fallback, observed 2026-05-21T15:54:15.401556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-21T15:52:27.900929Z digest=sha256:cb4e07c2cafef1bd963a70eeae61e6c0ccfd8ced379725168955914867ce4a83

Pith citing papers

Observation 895a00d0-d60c-4646-8944-d25a6f6bf5e6 · inbound

OC-Distill: Ontology-aware Contrastive Learning with Cross-Modal Distillation for ICU Risk Prediction cites this paper.

OC-Distill: Ontology-aware Contrastive Learning with Cross-Modal Distillation for ICU Risk Prediction Do Sparse Autoencoders Identify Reasoning Features in Language Models?

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-02T16:08:01.995919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T16:08:01.995919Z digest=sha256:c8b775a8af127a9d1bc76dc71d4efd1a45bafbdb35566d8f629876c9d92dc357