INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_35.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.35.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

illus

-0.30

áº§

-0.26

å½¢çĬ¶

-0.26

ç¡Ĳ

-0.26

åĳĪçİ°åĩº

-0.26

çļĦä½įç½®

-0.25

çļĦçľŁå®ŀæĢ§

-0.25

vements

-0.24

æ¼Ķç¤º

-0.24

 nett

-0.24

POSITIVE LOGITS

alink

0.29

azole

0.27

DownList

0.27

æ³ķåĪ¶

0.27

marshaller

0.27

AMED

0.26

 unemployed

0.25

InnerText

0.25

åĭŁéĽĨ

0.25

atype

0.25

Activations Density 15.779%

No Known Activations

This feature has no known activations.