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

pletely

-0.30

adata

-0.29

.boost

-0.26

 bound

-0.25

ç»ĻåŃ©åŃĲ

-0.24

çĹķè¿¹

-0.24

 mirror

-0.24

cre

-0.24

å¤§è¡Ĺ

-0.23

lio

-0.23

POSITIVE LOGITS

Ã©ny

0.25

zin

0.25

_piece

0.24

Denver

0.23

à¹Ĥà¸Ļ

0.23

 symp

0.23

(Func

0.23

ern

0.23

inned

0.23

 precis

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.