INDEX

Explanations

theft

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åīįæľŁ

-0.28

ç¾¤

-0.28

SetName

-0.26

","");↵

-0.26

ä¸Ģé¡¿

-0.25

"),"

-0.25

azzi

-0.25

trib

-0.24

äººæ°ĳç¾¤ä¼Ĺ

-0.24

_named

-0.24

POSITIVE LOGITS

æ¢¢

0.29

Ð³ÑĢÐ°Ð´

0.25

 dimension

0.25

vang

0.25

ippet

0.25

 giÃ¡c

0.24

dimension

0.23

ureau

0.23

vore

0.23

 slots

0.23

Activations Density 40.351%

theft

No Comments

No Known Activations