INDEX

Explanations

code and class names

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸įåĩº

-0.26

å¥¹æĺ¯

-0.25

ì»·

-0.25

ä¸Ģå¤ľ

-0.25

ì°į

-0.25

cÃŃ

-0.24

cut

-0.24

arÄ±

-0.23

à¹Ĥà¸¢

-0.23

 gÃ¼ven

-0.23

POSITIVE LOGITS

ä½ĵéªĮ

0.27

ç¼¢

0.27

Ze

0.24

æĦŁåıĹ

0.24

ERVER

0.24

åĻ¨

0.23

åĮħ

0.23

ended

0.23

 underestimated

0.23

è°Ľ

0.23

Activations Density 0.972%

code and class names

No Comments

No Known Activations