INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

izedName

-0.25

urname

-0.25

 Earn

-0.25

poi

-0.25

ndata

-0.25

çľĭä»ĸ

-0.25

è¿ĽçĲĥ

-0.24

èĴ´

-0.24

ç²īä¸Ŀ

-0.24

åĮĿ

-0.24

POSITIVE LOGITS

çĲĨ

0.28

æĿĢäºº

0.26

Hor

0.26

 soph

0.25

floating

0.25

agh

0.24

register

0.24

adia

0.24

æ¸¸

0.24

 Cath

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.