INDEX

Explanations

education/computer architecture

np_max-act · gemini-2.0-flash

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

æĹ¥å¸¸

-0.34

arez

-0.28

èĲĮ

-0.28

_frontend

-0.27

 anthrop

-0.26

æ³¥

-0.26

ë§Ĳ

-0.25

 paced

-0.25

 mention

-0.25

plit

-0.25

POSITIVE LOGITS

èµ°ä¸ĭåİ»

0.28

itto

0.26

=format

0.26

ðŁĳĨ

0.25

æł¼å¼ı

0.25

 gÃ³

0.25

åľ¨åºĬä¸Ĭ

0.24

å°ĸåı«

0.24

=__

0.24

,col

0.23

Activations Density 0.219%

education/computer architecture

No Comments

No Known Activations