INDEX

Explanations

of

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

çļĦéĢŁåº¦

-0.28

_PI

-0.27

ä»Ł

-0.26

åıĳæĸĩ

-0.26

ipur

-0.25

ä¸įçķĻ

-0.25

ç½ĳé¦ĸé¡µ

-0.24

idding

-0.24

.TryParse

-0.24

çļĦåĬŀæ³ķ

-0.23

POSITIVE LOGITS

ç§ĳåŃ¦éĻ¢

0.28

äººå®¶

0.28

ç½®

0.28

åŃ¦ä¼ļ

0.25

lem

0.25

ä¸ĢåĪĻ

0.25

level

0.24

 indu

0.24

 resort

0.24

åĪ©

0.24

Activations Density 0.004%

of

No Comments

No Known Activations