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

ç¼©æ°´

-0.27

bane

-0.27

ä¸ĵåĮº

-0.27

ç®¦

-0.26

 scientifically

-0.26

_$

-0.25

 bÃ³

-0.24

 Pruitt

-0.24

 nigeria

-0.24

Cli

-0.24

POSITIVE LOGITS

oth

0.26

Ãªt

0.25

_protocol

0.25

å½¢

0.25

po

0.25

PLUS

0.25

å£«

0.25

mid

0.24

iat

0.24

med

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.