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

éĢĨ

-0.27

 rawData

-0.26

sheet

-0.25

&r

-0.25

&S

-0.25

ä¼ĹçŃ¹

-0.24

ç§ĺä¹¦éķ¿

-0.24

 SERIES

-0.24

teenth

-0.24

è±ģ

-0.24

POSITIVE LOGITS

åįĹå±±

0.27

Blo

0.26

bru

0.25

æīĭèħķ

0.25

bip

0.25

å¦Īå¦Ī

0.25

_browser

0.24

oc

0.24

 Mama

0.24

avior

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.