INDEX

Explanations

to

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 proven

-0.27

æľīè¿ĩ

-0.27

iros

-0.26

ãģĳãģ©

-0.26

enko

-0.24

-Encoding

-0.24

æ±Łæ¹ĸ

-0.24

æĽ´å¤ļä¿¡æģ¯

-0.24

 Certain

-0.24

 yielded

-0.24

POSITIVE LOGITS

çī¹éķ¿

0.28

å¯¹ä¼ģä¸ļ

0.26

åĽ´

0.25

/Math

0.25

ä¼ģä¸ļ

0.25

Ð°Ð½Ð¸Ñİ

0.25

åıįå¼¹

0.24

nameof

0.24

áº¥u

0.24

éªĨ

0.23

Activations Density 0.005%

to

No Comments

No Known Activations