INDEX

Explanations

Pil, Fil, or il

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

 succesfully

-0.28

åķĸ

-0.27

aised

-0.26

èĪ³

-0.26

 reproduction

-0.26

Synopsis

-0.25

æł¸å¿ĥåĮº

-0.25

 onSuccess

-0.25

istically

-0.25

 reproduce

-0.24

POSITIVE LOGITS

ä½ĵ

0.30

ç½ª

0.29

å¾Ģ

0.28

íĮĲ

0.26

 License

0.25

èº«ä½ĵ

0.25

è½®

0.25

 Vanity

0.24

glas

0.24

å½¹

0.24

Activations Density 0.001%

Pil, Fil, or il

No Comments

No Known Activations