INDEX

Explanations

scientific information

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_30.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.30.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

plane

-0.28

çĩ®

-0.26

 plane

-0.26

brick

-0.25

éĿ¢

-0.25

astically

-0.24

éļ°

-0.24

 panc

-0.24

å¹³éĿ¢

-0.24

planes

-0.24

POSITIVE LOGITS

è¿ĩ

0.31

çŃĴ

0.30

ç¢§

0.29

oss

0.29

WO

0.28

ayo

0.28

uggling

0.27

uggle

0.26

æį¢

0.25

(iv

0.25

Activations Density 0.889%

scientific information

No Comments

No Known Activations