INDEX

Explanations

image processing/optics

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

otle

-0.30

)set

-0.27

cmc

-0.25

åĳ¨åĽ´

-0.24

 Stroke

-0.24

CM

-0.24

 judge

-0.24

è®®

-0.24

-road

-0.23

ç¢į

-0.23

POSITIVE LOGITS

unities

0.27

ç²īä¸Ŀ

0.26

ystate

0.26

çĻ¸

0.26

formed

0.26

sthrough

0.25

collision

0.25

strt

0.25

oola

0.25

 collision

0.24

Activations Density 0.013%

image processing/optics

No Comments

No Known Activations