© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

QWEN3-32B · 32-RESID-BATCHTOPK-65K · 12386 ｜ Neuronpedia

Home
Qwen3-32B
32-RESID-BATCHTOPK-65K
12386

INDEX

Explanations

any one

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Negative Logits

asio

-0.10

anium

-0.09

æ²ģ

-0.09

ijn

-0.09

æ¼Ķ

-0.08

idge

-0.08

uler

-0.08

ë¦´

-0.08

rios

-0.08

ENA

-0.08

POSITIVE LOGITS

 else

0.13

else

0.12

 Else

0.11

ç»¼åĲĪä½ĵ

0.11

Else

0.10

æĻ®éģįåŃĺåľ¨

0.10

æ¬¢åĸľ

0.10

å¤Ħå¤Ħ

0.10

 elsewhere

0.09

åĪ¹

0.09

Activations Density 0.073%

No Known Activations