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

ç»Łé¢Ĩ

-0.27

åĬ³

-0.26

çīµ

-0.26

bull

-0.25

 spokes

-0.25

 Couples

-0.25

ç»§ç»Ń

-0.25

è½®

-0.25

å¤§å§Ĳ

-0.25

åĢ¾

-0.24

POSITIVE LOGITS

 hygiene

0.28

 decorated

0.25

sug

0.24

 early

0.24

anship

0.24

anmar

0.24

{!!

0.24

Ð½ÐµÐ¹

0.23

åĩºéģĵ

0.23

egrated

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.