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

regex

-0.27

 Arithmetic

-0.26

áº¥u

-0.25

atak

-0.25

åĲ¬åıĸ

-0.24

ä¼łå¯¼

-0.23

uess

-0.23

 regex

-0.23

 createState

-0.22

 authDomain

-0.22

POSITIVE LOGITS

ifix

0.28

 succesfully

0.28

 ÑĥÑģÐ¿ÐµÑĪ

0.28

bound

0.26

ä¸ĢæĹı

0.26

(cf

0.25

efs

0.24

 future

0.24

rox

0.24

æľªæĿ¥

0.24

Activations Density 0.065%

No Known Activations

This feature has no known activations.