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

çĿĢä»ĸ

-0.27

ifiÃ©

-0.25

agog

-0.24

adamente

-0.24

enne

-0.24

emale

-0.23

ä¸¥éĩį

-0.23

ildo

-0.23

 beforeSend

-0.23

WidgetItem

-0.23

POSITIVE LOGITS

ä¸Ģç¾¤äºº

0.29

-č↵

0.26

rgan

0.25

ber

0.25

ras

0.25

ä¸Ģç¯ĩ

0.24

å¹²ä»Ģä¹Ī

0.23

çº¯æ´ģ

0.23

 discrim

0.23

.Hit

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.