INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Cree

-0.29

 Indicator

-0.27

çĵľ

-0.27

å¯¹åºĶçļĦ

-0.26

ä»£è¡¨

-0.26

 FEATURES

-0.26

Currently

-0.25

 diagonal

-0.25

ç¿¡ç¿ł

-0.24

 Decimal

-0.24

POSITIVE LOGITS

onne

0.28

æī§æĦı

0.26

æĿ³

0.25

ç»Ħç»ĩé¢Ĩå¯¼

0.24

æĮ½

0.24

 chants

0.23

alette

0.23

 vehement

0.23

åĩłä¸ª

0.23

ä¸ĢèĦļ

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.