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

æĿĥ

-0.28

ption

-0.26

æĿĥå¨ģ

-0.26

äºĴè¡¥

-0.26

>v

-0.25

äºĶæĺŁ

-0.25

 Opportunities

-0.24

ä¼łçĲĥ

-0.24

 Autor

-0.24

.atom

-0.24

POSITIVE LOGITS

nds

0.28

æĭĶ

0.27

èµĽåĮº

0.27

 figsize

0.25

mbH

0.25

 $↵↵

0.25

urg

0.25

elon

0.24

unny

0.24

.ico

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.