INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

seau

-0.29

irse

-0.28

 fixture

-0.26

 appell

-0.25

ppers

-0.25

 miejs

-0.25

rf

-0.24

åĶ¿

-0.24

ey

-0.24

ç²¾

-0.23

POSITIVE LOGITS

ryan

0.27

éĥ½èĥ½

0.26

æĺİæĹ¥

0.26

éĥ½åı¯ä»¥

0.26

parable

0.25

alist

0.25

alien

0.24

asted

0.24

 Vill

0.24

æİĽ

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.