INDEX

Explanations

historical data and computer processes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å®īåħ¨æĦŁ

-0.29

æ©Ĳ

-0.27

 Ð¾ÑĤÐ´ÑĭÑħ

-0.26

å¹¸ç¦ıæĦŁ

-0.25

-policy

-0.25

ç¾Ŀ

-0.25

Ð¶Ð´

-0.25

æĶ¾å¿ĥ

-0.25

alloca

-0.25

izzly

-0.24

POSITIVE LOGITS

ç¼ĸåĨĻ

0.37

 writing

0.36

 writers

0.34

æĴ°åĨĻ

0.34

 Writing

0.32

 manuscripts

0.32

çºĤ

0.31

 translations

0.30

 compilation

0.30

æĴ°

0.30

Activations Density 0.000%

historical data and computer processes

No Comments

No Known Activations