INDEX

Explanations

reviews/commentary

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

äººå¤§

-0.32

çľĭä»ĸ

-0.30

.microsoft

-0.28

æĪĲåĬŁçİĩ

-0.26

è¶£åĳ³

-0.26

ëĿ¼ëıĦ

-0.25

åŁŁ

-0.25

 Ð·Ð°Ð±

-0.25

thumb

-0.24

 Trap

-0.24

POSITIVE LOGITS

uyen

0.27

croft

0.26

lian

0.26

ective

0.26

illery

0.25

FFECT

0.25

å¼ķ

0.25

(rawValue

0.25

æĺ¯ä»Ģä¹Īåĳ¢

0.24

 Carson

0.24

Activations Density 0.005%

reviews/commentary

No Comments

No Known Activations