INDEX

Explanations

greater

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 great

-0.39

great

-0.34

 GREAT

-0.34

Great

-0.33

 Great

-0.30

ä¼Łå¤§çļĦ

-0.29

å·¨å¤§

-0.27

 Greater

-0.27

(Convert

-0.26

æľīæĹ¶

-0.26

POSITIVE LOGITS

 degrees

0.55

 degree

0.49

åº¦

0.47

-degree

0.41

degree

0.39

 Degree

0.39

Degree

0.39

 amounts

0.38

 than

0.37

 numbers

0.37

Activations Density 0.022%

greater

No Comments

No Known Activations