INDEX

Explanations

millions

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

åı¸

-0.31

 criteria

-0.29

criteria

-0.28

cr

-0.27

 Criteria

-0.27

æ¬¹

-0.27

æłĩå¿Ĺ

-0.27

(criteria

-0.25

egis

-0.25

-cr

-0.25

POSITIVE LOGITS

million

0.39

çĻ¾ä¸ĩ

0.37

 million

0.36

 Million

0.35

 milhÃµes

0.33

 Millions

0.33

 millions

0.32

æĺ¯éĿŀ

0.28

 Ð¼Ð¸Ð»Ð»Ð¸Ð¾Ð½

0.28

mg

0.28

Activations Density 0.009%

millions

No Comments

No Known Activations