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

anja

-0.30

rene

-0.29

astes

-0.28

ewe

-0.27

è°¢è°¢ä½ł

-0.26

wich

-0.26

igli

-0.26

éĹ®ä»ĸ

-0.25

.tim

-0.25

æĲ¬

-0.25

POSITIVE LOGITS

èģĮåĬ¡

0.28

 Scalar

0.26

 scalar

0.26

.ResponseBody

0.25

åıĮéĩį

0.24

UBLIC

0.24

ppelin

0.24

ah

0.24

hips

0.24

 Happy

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.