INDEX

Explanations

exhibitions

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

 bluff

-0.31

hoot

-0.28

plen

-0.26

eliness

-0.25

/cgi

-0.25

é¢Ŀå¤´

-0.25

 Ð°Ð´Ð¼Ð¸Ð½Ð¸ÑģÑĤÑĢÐ°ÑĨÐ¸

-0.25

setData

-0.24

setIcon

-0.24

 BinaryTree

-0.24

POSITIVE LOGITS

agger

0.30

éĥİ

0.26

assemble

0.25

Ø³ØªØ§ÙĨ

0.24

è´¹

0.24

å®¤åĨħ

0.23

 endorsements

0.23

 Positions

0.23

è¡Ģèħ¥

0.23

_NE

0.23

Activations Density 0.002%

exhibitions

No Comments

No Known Activations