INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

indo

-0.27

uter

-0.26

æĹıèĩªæ²»åİ¿

-0.24

ä¸ĩéĩĮ

-0.24

åįıè°ĥåıĳå±ķ

-0.24

>>=

-0.24

ä»Ģä¹ĪæĦıæĢĿ

-0.24

 trÃ¡i

-0.23

'article

-0.23

syn

-0.23

POSITIVE LOGITS

rike

0.28

æĮ¥

0.27

etter

0.26

rix

0.26

 dÃ¼r

0.25

 Graham

0.25

alytics

0.25

likely

0.24

æ°´ç®¡

0.24

Å¡t

0.23

Activations Density 0.577%

No Known Activations

This feature has no known activations.