INDEX

Explanations

China

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_30.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.30.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

petto

-0.29

ng

-0.28

nger

-0.28

çļĦæĥħ

-0.27

åħĪ

-0.27

LIN

-0.27

brook

-0.26

/cop

-0.26

åħħ

-0.25

anga

-0.25

POSITIVE LOGITS

 Chinese

0.46

 Tian

0.45

Chinese

0.45

 Beijing

0.42

 chinese

0.40

 China

0.40

China

0.39

 Alibaba

0.39

æĺ¯ä¸ŃåĽ½

0.39

 Guang

0.38

Activations Density 1.073%

China

No Comments

No Known Activations