INDEX

Explanations

uncertainty

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çīº

-0.26

/al

-0.26

æµ´

-0.26

crement

-0.26

æĸ°éĻĪä»£è°¢

-0.24

åºĲ

-0.24

ants

-0.23

æ¸ĹéĢı

-0.23

 hÃ¨

-0.23

epar

-0.23

POSITIVE LOGITS

 ambiguous

1.01

 ambiguity

0.98

ä¸įç¡®å®ļ

0.98

 uncertain

0.95

 unclear

0.89

 uncertainty

0.87

æ¨¡ç³Ĭ

0.84

ä¸įç¡®å®ļæĢ§

0.82

Unc

0.79

 ambigu

0.77

Activations Density 0.002%

uncertainty

No Comments

No Known Activations