INDEX

Explanations

Article/publication

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

andalone

-0.26

éĶĢ

-0.25

.tell

-0.25

inos

-0.24

éĢļè¡Įè¯ģ

-0.23

Jub

-0.23

åģ·åģ·

-0.23

æ¼Ĥæµģ

-0.23

ä¸ĭæ²ī

-0.23

 Tell

-0.23

POSITIVE LOGITS

 props

0.29

[]

0.27

 prop

0.25

	props

0.25

 colleg

0.25

<![

0.25

(props

0.24

åıĮèµ¢

0.24

AlgorithmException

0.24

 commanded

0.24

Activations Density 2.958%

Article/publication

No Comments

No Known Activations