© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

QWEN3-4B · 4-TRANSCODER-HP · 244 ｜ Neuronpedia

Home
Qwen3-4B
4-TRANSCODER-HP
244

INDEX

Explanations

medical texts

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

mwhanna/qwen3-4b-transcoders/layer_4.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.4.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

thern

-0.26

æŀ³

-0.26

vester

-0.25

ugen

-0.25

fleet

-0.24

cks

-0.24

æĭĦ

-0.24

lined

-0.24

 thereof

-0.24

çĹĺ

-0.23

POSITIVE LOGITS

0.29

sig

0.29

éĩĮ

0.28

plib

0.26

suite

0.26

itÃ©s

0.26

'',

0.26

Ð¾Ð²Ð¸Ñĩ

0.25

''

0.25

ÐµÐ½ÐºÐ¾

0.25

Activations Density 0.014%

No Known Activations