INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

__),

-0.31

astic

-0.26

é¡¯

-0.25

çŁ¥éģĵèĩªå·±

-0.25

ooth

-0.25

 poles

-0.25

bro

-0.25

iais

-0.25

fil

-0.24

ades

-0.24

POSITIVE LOGITS

èĴ½

0.30

tape

0.28

ropa

0.27

æ²ī

0.27

è¿ĲèĲ¥åķĨ

0.26

Down

0.25

æ²īéĩį

0.24

åıĤ

0.24

ä¸Ģå¤§æī¹

0.24

Ð¿Ð¸ÑģÑĮ

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.