INDEX

Explanations

News articles

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åıĪæľī

-0.27

 graded

-0.27

 entitled

-0.27

å»ºç«ĭäºĨ

-0.27

uds

-0.26

åĨį

-0.26

.getTitle

-0.25

itulo

-0.25

ä½ķ

-0.24

ÑħÐ¸

-0.24

POSITIVE LOGITS

ç½ĳç«Ļ

0.32

 Website

0.29

Website

0.28

 website

0.28

è½¼

0.28

website

0.27

 Websites

0.27

ä¹ĭå£°

0.27

|string

0.26

 ÑģÐ°Ð¹

0.25

Activations Density 0.003%

News articles

No Comments

No Known Activations