INDEX

Explanations

of

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

craft

-0.29

wen

-0.28

èµħ

-0.25

ç½ķ

-0.25

drug

-0.24

brate

-0.24

ä½Ĳ

-0.24

èĽĽ

-0.24

éħįæĸĻ

-0.24

è´°

-0.24

POSITIVE LOGITS

_PROD

0.27

æ¹Ķ

0.25

æīĵæŀ¶

0.25

,âĢ¦↵↵

0.24

/net

0.24

å¥½è¿Ĳ

0.24

è¡Ģ

0.23

bservice

0.23

 compatibility

0.23

.Driver

0.23

Activations Density 0.053%

of

No Comments

No Known Activations