INDEX

Explanations

cooking meat

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_12.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.12.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sapi

-0.29

èŀºä¸Ŀ

-0.26

gles

-0.25

roups

-0.25

ghan

-0.24

 Cooler

-0.24

 ench

-0.24

ncia

-0.24

.El

-0.23

ogie

-0.23

POSITIVE LOGITS

å±ķåĵģ

0.28

ä¹ĭå£°

0.26

åĹħ

0.25

 Hait

0.25

åİ¿çº§

0.24

åĳķåĲĲ

0.24

">#

0.24

ä¸Ģåı·

0.24

ç²³

0.24

 spot

0.23

Activations Density 0.001%

cooking meat

No Comments

No Known Activations