© 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 · 6759 ｜ Neuronpedia

Home
Qwen3-32B
32-RESID-BATCHTOPK-65K
6759

INDEX

Explanations

women

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

ment

-0.14

er

-0.13

Ø§

-0.12

ional

-0.12

mente

-0.12

(es

-0.11

ity

-0.10

ses

-0.10

ate

-0.10

ible

-0.09

POSITIVE LOGITS

folk

0.13

hir

0.11

archy

0.10

ä¸ĢèĪ¬çļĦ

0.10

aces

0.09

0.09

ouve

0.09

ä¹ĭåŁİ

0.09

igar

0.08

èŁł

0.08

Activations Density 0.053%

No Known Activations