INDEX

Explanations

interjections

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

éķĿ

-0.27

è¯Ħè®®

-0.26

eson

-0.26

 centers

-0.25

ĥģ

-0.25

emble

-0.25

æī°ä¹±

-0.25

 metic

-0.25

 jdbc

-0.24

ARCHAR

-0.24

POSITIVE LOGITS

è¿ĻäºĽä¸ľè¥¿

0.30

åľ¨è¿Ļæĸ¹éĿ¢

0.28

ascript

0.27

ian

0.26

ç¬¬äºĮæī¹

0.26

availability

0.25

Î¹

0.25

 Availability

0.25

æµĩ

0.25

 achievement

0.24

Activations Density 0.007%

interjections

No Comments

No Known Activations