INDEX

Explanations

information

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

åıĳåĬ¨

-0.30

ä½ı

-0.29

 âĨĳ

-0.28

arrow

-0.27

ä¸ĭæĿ¥

-0.27

ate

-0.26

å»Ĭ

-0.26

 Â·

-0.26

è¡Ĺ

-0.25

 arrange

-0.25

POSITIVE LOGITS

presso

0.26

rms

0.26

è·

0.26

ibia

0.26

rms

0.25

 volum

0.25

èıŁ

0.25

 Gund

0.25

ä¹Łä¸įä¾ĭå¤ĸ

0.25

å®¢æľį

0.24

Activations Density 0.016%

information

No Comments

No Known Activations