INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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¯ĵ

-0.28

 Legs

-0.26

isease

-0.26

ä½¿æĪĳ

-0.26

è¡¨çİ°åĩº

-0.25

çģ¶

-0.25

omat

-0.25

çļĦä¼ĺçĤ¹

-0.25

velop

-0.24

legs

-0.24

POSITIVE LOGITS

dup

0.28

dux

0.28

èĩ³åħ³éĩįè¦ģ

0.27

 rare

0.27

anax

0.27

 Rare

0.26

 reconsider

0.26

axed

0.26

far

0.25

 weit

0.25

Activations Density 0.040%

No Known Activations

This feature has no known activations.