© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

QWEN3-32B · 32-RESID-BATCHTOPK-65K · 52577 ｜ Neuronpedia

Home
Qwen3-32B
32-RESID-BATCHTOPK-65K
52577

INDEX

Explanations

The process

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

Not in Any Lists

No Comments

Negative Logits

aps

-0.09

åĸ·

-0.09

ä½¬

-0.09

åĪ¶æĪĲ

-0.09

amo

-0.08

è·³

-0.08

åĻ´

-0.08

atto

-0.08

hop

-0.08

 Ð±Ð°

-0.08

POSITIVE LOGITS

 process

0.10

 Ð¿ÑĢÐ¾ÑĨÐµÑģÑģ

0.10

è¿Ľç¨ĭ

0.10

 Process

0.10

process

0.09

 candidacy

0.09

è¿ĩç¨ĭ

0.09

aina

0.08

oving

0.08

 Sacred

0.08

Activations Density 0.031%

No Known Activations