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

nameof

-0.29

æĢ§å¼º

-0.27

leine

-0.26

eve

-0.26

åįıä½ľ

-0.25

kick

-0.24

ModelIndex

-0.24

 Churchill

-0.24

 GetType

-0.24

adiens

-0.24

POSITIVE LOGITS

 furn

0.28

 ruler

0.26

wax

0.26

 pron

0.25

Âł

0.25

suf

0.25

irth

0.24

 realiza

0.24

oph

0.23

 Ã©

0.23

Activations Density 0.003%

No Known Activations

This feature has no known activations.