INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

_CNTL

-0.31

ativity

-0.28

redo

-0.27

è´¬

-0.27

hoff

-0.26

ä¸¾

-0.26

ewidth

-0.25

æ¶ķ

-0.25

ee

-0.25

DbType

-0.25

POSITIVE LOGITS

 style

0.30

 Style

0.29

-bearing

0.27

æĽ´å¤ļä¿¡æģ¯

0.26

 contributing

0.26

 supporting

0.25

-chan

0.25

 gá»£i

0.25

 gist

0.25

ben

0.24

Activations Density 24.618%

No Known Activations

This feature has no known activations.