INDEX

Explanations

stimulus

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

æĲĶ

-0.32

unan

-0.30

 central

-0.27

 clientele

-0.26

)((((

-0.25

ackle

-0.25

Ø¹ÙħØ§Ø±

-0.25

æı´

-0.25

aklÄ±

-0.24

central

-0.24

POSITIVE LOGITS

cip

0.31

cpt

0.26

å¤±è´¥

0.25

Asi

0.24

äº¤éĢļå®īåħ¨

0.24

çķ¿

0.24

 perv

0.24

 injuring

0.23

Ð¸Ð¼Ð²

0.23

 lesser

0.23

Activations Density 0.282%

stimulus

No Comments

No Known Activations