INDEX

Explanations

software and technical documentation

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

ä¸ºä¸ŃåĽ½

-0.29

åıĳçĶŁåıĺåĮĸ

-0.28

 Piece

-0.28

åıĺåĮĸ

-0.26

ignon

-0.26

heck

-0.26

è¿ĻåĿĹ

-0.26

ä¸įä½İäºİ

-0.25

 Infer

-0.25

 piece

-0.25

POSITIVE LOGITS

 applies

0.29

çº§ä»¥ä¸Ĭ

0.28

yo

0.27

 newObj

0.26

åı¯è¡ĮæĢ§

0.26

heritance

0.25

ForObject

0.25

 instead

0.25

akes

0.25

.retrieve

0.24

Activations Density 0.001%

software and technical documentation

No Comments

No Known Activations