INDEX

Explanations

general English text

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

æľĢå°ĳ

-0.30

åıĳæĸĩ

-0.28

ponge

-0.25

 least

-0.24

æ°ĳèĲ¥ç»ıæµİ

-0.23

least

-0.23

æ²¡åħ³ç³»

-0.23

èµ¶å¿«

-0.23

orda

-0.23

èĻŀ

-0.23

POSITIVE LOGITS

 larger

0.80

æĽ´å¤§çļĦ

0.73

 bigger

0.73

æĽ´å¤§

0.69

 Larger

0.68

 heavier

0.56

æĽ´é«ĺ

0.52

 broader

0.50

 longer

0.48

é«ĺçº§

0.48

Activations Density 0.001%

general English text

No Comments

No Known Activations