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

èµİ

-0.30

Õ¿

-0.27

åľ¨åŃ¦æł¡

-0.26

åīįç½®

-0.26

lie

-0.26

ve

-0.26

arin

-0.25

azes

-0.25

á»Ĺi

-0.25

ptic

-0.25

POSITIVE LOGITS

angkan

0.30

anship

0.29

ropy

0.28

åıĭæĥħéĵ¾æİ¥

0.26

 Symbol

0.25

è¿ĺæĥ³

0.25

ì°°

0.25

customize

0.25

åĬłæĮģ

0.24

åıĭå¥½

0.24

Activations Density 0.002%

No Known Activations

This feature has no known activations.