INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

æ¯ıä¸Ģä½į

-0.31

éĻ¤æŃ¤ä¹ĭå¤ĸ

-0.29

è¡įçĶŁ

-0.28

etcode

-0.26

orate

-0.26

è¢ĭ

-0.26

mods

-0.25

æŃ¤äºº

-0.25

äºĤ

-0.25

wort

-0.25

POSITIVE LOGITS

imonials

0.27

imon

0.26

åį«

0.26

 triple

0.25

 Triple

0.25

åĩ½

0.25

legalArgumentException

0.25

 cÃ¢n

0.24

ÐµÐ¹

0.24

ler

0.24

Activations Density 0.106%

No Known Activations

This feature has no known activations.