INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Extra

-0.28

 Extra

-0.28

ivate

-0.26

weit

-0.26

ogie

-0.25

ivative

-0.25

(extra

-0.25

scenes

-0.25

ä¸įèĥ½åĨį

-0.25

 guts

-0.24

POSITIVE LOGITS

å»ī

0.31

se

0.28

0.27

..

0.27

[L

0.27

.conf

0.25

Utility

0.25

[a

0.25

 taxes

0.25

Ø¨ÙĬÙĦ

0.25

Activations Density 1.635%

No Known Activations

This feature has no known activations.