Neel Nanda

Karma: 14,633

How well do models follow their constitutions?

aryaj, Senthooran Rajamanoharan and Neel Nanda

12 Mar 2026 0:07 UTC

94 points

5 comments26 min readLW link

Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation

Bartosz Cywiński, Helena Casademunt, Khoi Tran, aryaj, Sam Marks and Neel Nanda

9 Mar 2026 18:50 UTC

30 points

2 comments5 min readLW link

Current activation oracles are hard to use

aryaj, Senthooran Rajamanoharan and Neel Nanda

3 Mar 2026 19:33 UTC

77 points

3 comments16 min readLW link

How to Design Environments for Understanding Model Motives

gersonkroiz, aditya singh, Senthooran Rajamanoharan and Neel Nanda

2 Mar 2026 7:14 UTC

42 points

0 comments10 min readLW link

Why Did My Model Do That? Model Incrimination for Diagnosing LLM Misbehavior

aditya singh, gersonkroiz, Senthooran Rajamanoharan and Neel Nanda

27 Feb 2026 3:20 UTC

51 points

1 comment78 min readLW link

models have some pretty funny attractor states

aryaj, Senthooran Rajamanoharan and Neel Nanda

12 Feb 2026 21:14 UTC

266 points

38 comments18 min readLW link

It Is Reasonable To Research How To Use Model Internals In Training

Neel Nanda8 Feb 2026 3:44 UTC

101 points

15 comments4 min readLW link

Test your interpretability techniques by de-censoring Chinese models

Khoi Tran, aryaj, Senthooran Rajamanoharan and Neel Nanda

15 Jan 2026 16:33 UTC

90 points

14 comments20 min readLW link

Global CoT Analysis: Initial attempts to uncover patterns across many chains of thought

Riya Tyagi, daria, Arthur Conmy and Neel Nanda

13 Jan 2026 20:40 UTC

52 points

0 comments18 min readLW link

Brief Explorations in LLM Value Rankings

Tim Hua, Josh Engels, Neel Nanda and Senthooran Rajamanoharan

12 Jan 2026 18:16 UTC

37 points

1 comment11 min readLW link

Principled Interpretability of Reward Hacking in Closed Frontier Models

gersonkroiz, aditya singh, Senthooran Rajamanoharan and Neel Nanda

1 Jan 2026 16:37 UTC

24 points

0 comments23 min readLW link

Steering RL Training: Benchmarking Interventions Against Reward Hacking

ariaw, Josh Engels and Neel Nanda

29 Dec 2025 21:55 UTC

58 points

10 comments19 min readLW link

Announcing Gemma Scope 2

CallumMcDougall, Arthur Conmy, János Kramár, Tom Lieberum, Senthooran Rajamanoharan and Neel Nanda

22 Dec 2025 21:56 UTC

95 points

1 comment2 min readLW link

Can we interpret latent reasoning using current mechanistic interpretability tools?

Bartosz Cywiński, Bart Bussmann, Arthur Conmy, Josh Engels, Neel Nanda and Senthooran Rajamanoharan

22 Dec 2025 16:56 UTC

37 points

0 comments9 min readLW link

[Paper] Difficulties with Evaluating a Deception Detector for AIs

bilalchughtai, lewis smith and Neel Nanda

3 Dec 2025 20:07 UTC

30 points

2 comments6 min readLW link

(arxiv.org)

How Can Interpretability Researchers Help AGI Go Well?

Neel Nanda, Josh Engels, Senthooran Rajamanoharan, Arthur Conmy, bilalchughtai, CallumMcDougall, János Kramár and lewis smith

1 Dec 2025 13:05 UTC

66 points

1 comment14 min readLW link

A Pragmatic Vision for Interpretability

Neel Nanda, Josh Engels, Arthur Conmy, Senthooran Rajamanoharan, bilalchughtai, CallumMcDougall, János Kramár and lewis smith

1 Dec 2025 13:05 UTC

131 points

39 comments27 min readLW link

Current LLMs seem to rarely detect CoT tampering

Bartosz Cywiński, Bart Bussmann, Arthur Conmy, Neel Nanda, Senthooran Rajamanoharan and Josh Engels

19 Nov 2025 15:27 UTC

55 points

0 comments20 min readLW link

Steering Evaluation-Aware Models to Act Like They Are Deployed

Tim Hua, andrq, Sam Marks and Neel Nanda

30 Oct 2025 15:03 UTC

61 points

12 comments18 min readLW link

Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences

Julian Minder, Clément Dumas, Stewy Slocum and Neel Nanda

5 Sep 2025 12:11 UTC

54 points

2 comments7 min readLW link