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

selectors

-0.23

ç»ıåİĨè¿ĩ

-0.23

Cer

-0.23

.’”↵↵

-0.23

reads

-0.22

 transf

-0.22

 mined

-0.22

å¥¥æĸ¯

-0.22

èİ½

-0.22

_vue

-0.22

POSITIVE LOGITS

PC

0.25

ãģ¡

0.24

pun

0.24

åĵ¦

0.23

ovsky

0.23

cline

0.23

åŃ¦çĶŁ

0.23

åŁİåİ¿

0.22

æİ¨åĬ¨

0.22

olare

0.22

Activations Density 0.003%

No Known Activations

This feature has no known activations.