INDEX

Explanations

place names

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¸Ĳ

-0.28

oola

-0.28

GP

-0.28

åĨľåİĨ

-0.26

åĪ°äºĨ

-0.25

åĪ¶è®¢

-0.24

å¹¹

-0.24

çĶŁäº§è½¦éĹ´

-0.24

 builders

-0.24

è¿ĺæĺ¯è¦ģ

-0.24

POSITIVE LOGITS

hiba

0.30

æļ¹

0.28

hani

0.27

 cylinder

0.27

Ð¢ÐĲ

0.27

estone

0.27

etur

0.26

ä¸ĢåŃĹ

0.26

åĮĿ

0.26

 cylinders

0.25

Activations Density 0.001%

place names

No Comments

No Known Activations