INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ivities

-0.27

ickle

-0.26

ÄŁini

-0.26

suming

-0.25

åĨįåİ»

-0.25

æ´ĩ

-0.25

witter

-0.24

/tree

-0.24

éģĳ

-0.24

è··

-0.24

POSITIVE LOGITS

èģĶç³»

0.26

ç¾½æ¯Ľ

0.26

 condensed

0.25

åĪ»

0.25

 itself

0.24

èģĶç³»æĸ¹å¼ı

0.24

æµ©

0.24

æĵįçºµ

0.24

ç»Ħç»ĩ

0.24

 permanent

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.