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

åĬŀäºĭ

-0.28

upp

-0.26

uling

-0.26

wald

-0.26

allah

-0.25

 spoilers

-0.24

-mouth

-0.24

OTES

-0.24

spi

-0.24

nar

-0.24

POSITIVE LOGITS

åĳ¨å²ģ

0.28

ä¸įåİ»

0.27

cimal

0.25

arius

0.25

owa

0.24

 TObject

0.24

ario

0.24

 appeal

0.24

å¼ºåĮĸ

0.24

ace

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.