© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

QWEN3-32B · 32-RESID-BATCHTOPK-65K · 52311 ｜ Neuronpedia

Home
Qwen3-32B
32-RESID-BATCHTOPK-65K
52311

INDEX

Explanations

extracting

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

zilla

-0.10

nings

-0.10

liness

-0.10

acre

-0.09

boy

-0.09

alty

-0.09

atically

-0.09

boat

-0.09

ister

-0.09

uation

-0.09

POSITIVE LOGITS

à¹Į

0.12

ively

0.11

ÑĢÐ°Ð

0.09

rema

0.09

ivism

0.09

ordinary

0.09

OrUpdate

0.09

Aur

0.08

ters

0.08

Ø²Ø§Ø¯

0.08

Activations Density 0.045%

No Known Activations