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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç«¯æŃ£

-0.27

ä¼ª

-0.26

etheless

-0.25

 personals

-0.25

Ð·Ð´

-0.24

åľ¨åºĬä¸Ĭ

-0.24

 Homepage

-0.24

\Migration

-0.24

åİŁæłĩé¢ĺ

-0.24

æķħå±ħ

-0.24

POSITIVE LOGITS

ÑĤÐ°Ð¹

0.29

áº§m

0.27

**(

0.26

åħģ

0.25

?(

0.25

à¸Ńà¸Ļ

0.25

 tolerate

0.25

æīĪ

0.24

)&&(

0.24

 Ellis

0.24

Activations Density 0.003%

of

No Comments

No Known Activations