INDEX

Explanations

center

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

arrow

-0.30

stick

-0.27

enh

-0.26

ç»ĵå©ļ

-0.25

fic

-0.25

 either

-0.24

ITHER

-0.24

é©»

-0.24

TypeDef

-0.24

sticks

-0.24

POSITIVE LOGITS

 bÄĥng

0.28

ä»Ģä¹Īåĳ¢

0.26

casting

0.26

å®ļä»·

0.25

 bombings

0.25

 seiz

0.24

éĴ£

0.24

åħīå½±

0.24

ä¿Ŀå®Ī

0.24

(loss

0.24

Activations Density 0.085%

center

No Comments

No Known Activations