INDEX

Explanations

technical text

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

ä¾Ľå¤§å®¶

-0.32

å¢ŀ

-0.27

 rider

-0.27

å¢ŀèĩ³

-0.26

 SUBJECT

-0.25

æµ·æ·Ģ

-0.25

eming

-0.25

èŁł

-0.24

ä½¿ä¹ĭ

-0.24

Amazon

-0.24

POSITIVE LOGITS

 FranÃ§ois

0.40

 Julien

0.37

 France

0.36

FranÃ§ois

0.35

France

0.33

ienne

0.33

æ³ķåĽ½

0.33

 Marseille

0.33

 FranÃ§ais

0.32

æ¹ĺè¥¿

0.32

Activations Density 0.007%

technical text

No Comments

No Known Activations