© 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

QWEN3-4B · 9-TRANSCODER-HP · 29197 ｜ Neuronpedia

Home
Qwen3-4B
9-TRANSCODER-HP
29197

INDEX

Explanations

food

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

mwhanna/qwen3-4b-transcoders/layer_9.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.9.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Negative Logits

ç¼©

-0.28

mec

-0.27

åĩºæĿ¥

-0.26

 sinon

-0.26

Ã¦nd

-0.26

_except

-0.26

èģĮ

-0.25

RAINT

-0.25

ast

-0.25

ughs

-0.25

POSITIVE LOGITS

decl

0.27

-TV

0.26

 Sachs

0.25

![

0.24

åĳ½

0.24

loth

0.24

åĲįåı«

0.24

åĢĴåľ¨

0.24

æ»¡

0.24

Ups

0.23

Activations Density 0.501%

No Known Activations