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

Negative Logits

cac

-0.28

cks

-0.25

ç»Ļå¥¹

-0.25

_BS

-0.24

 Deng

-0.24

 polarization

-0.24

ERT

-0.23

'][]

-0.23

 backs

-0.23

 convent

-0.23

POSITIVE LOGITS

åŁº

0.27

aning

0.27

æĭ¿

0.26

ax

0.26

fat

0.25

ä¸ĭæĸ¹

0.25

fig

0.25

 succeed

0.25

odd

0.24

ishes

0.24

Activations Density 0.003%

No Known Activations

This feature has no known activations.