INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æľºåĻ¨

-0.30

é³ı

-0.25

Tail

-0.25

Machine

-0.24

chair

-0.24

çī©

-0.23

çªĴ

-0.23

artisan

-0.23

 myself

-0.23

machine

-0.23

POSITIVE LOGITS

ä»ĸå¯¹

0.28

çº²

0.28

ä¸ĩä¸ª

0.28

FE

0.27

tees

0.27

èĨº

0.27

COME

0.26

å¦Ļ

0.26

éĹ®ä»ĸ

0.25

([...

0.25

Activations Density 0.150%

No Known Activations

This feature has no known activations.