INDEX

Explanations

opportunity

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

LEX

-0.29

è¿ĺå¥½

-0.28

orable

-0.28

 MOCK

-0.27

UILayout

-0.25

ffective

-0.25

quals

-0.24

resse

-0.24

 Sized

-0.24

eus

-0.24

POSITIVE LOGITS

Del

0.31

DEL

0.30

Del

0.30

 Contr

0.29

 contr

0.29

del

0.29

del

0.28

xc

0.28

æ´»åĬ¨ä¸Ń

0.27

 caption

0.26

Activations Density 0.001%

opportunity

No Comments

No Known Activations