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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 least

-0.31

ç¶ľ

-0.29

 Least

-0.29

Ð¾Ð¶

-0.28

least

-0.28

sx

-0.27

ogn

-0.27

æľĢå°ĳ

-0.27

empo

-0.26

-window

-0.26

POSITIVE LOGITS

çİ®

0.25

\@

0.25

Ð¸ÑĢÐ¾Ð²Ð°ÑĤÑĮ

0.25

atorial

0.24

èķ¤

0.24

.allow

0.24

ä½łèĩªå·±

0.24

åĿı

0.23

\/

0.23

é©³

0.23

Activations Density 0.009%

No Known Activations

This feature has no known activations.