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

 hesitation

-0.24

abilidad

-0.24

uja

-0.24

ç«ĭéĿ¢

-0.24

)new

-0.24

ernity

-0.24

è·¨åº¦

-0.23

kart

-0.23

ä¸Ńæĸ°

-0.23

gart

-0.23

POSITIVE LOGITS

ilon

0.32

èĢĮæĪĲ

0.30

ç²¾

0.28

è¯¥

0.27

bucks

0.27

èĢĮ

0.27

 Specifically

0.26

obi

0.26

åħ·ä½ĵ

0.26

åĬŁè¯¾

0.26

Activations Density 0.019%

No Known Activations

This feature has no known activations.