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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åıĤ

-0.32

äºİ

-0.30

Copyright

-0.29

çīĪæĿĥ

-0.28

åħ¶æ¬¡

-0.28

 Copyright

-0.27

HN

-0.26

uten

-0.26

emple

-0.25

 bland

-0.25

POSITIVE LOGITS

ipeg

0.31

oxy

0.27

 examining

0.27

âĩĵ

0.25

 Means

0.25

åĲįèªī

0.24

æŀķå¤´

0.24

åĤ¢

0.24

ä¿Ŀé²ľ

0.24

åľ°ä¸Ń

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.