INDEX

Explanations

leadership

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

èµ

-0.27

 possessions

-0.27

liament

-0.27

çıŃåŃĲ

-0.27

çıŃåŃĲæĪĲåĳĺ

-0.26

é¢Ĩå¯¼çıŃåŃĲ

-0.26

æŀĦ

-0.25

ellite

-0.25

 borough

-0.25

ãĥ¡ãĥĩãĤ£ãĤ¢

-0.24

POSITIVE LOGITS

 Infant

0.29

åīįå¤ķ

0.29

åīįä¸Ģå¤©

0.26

ahead

0.26

ä¹ĭäºī

0.25

 whites

0.25

 Ahead

0.25

 merit

0.25

tas

0.24

 ahead

0.24

Activations Density 1.372%

leadership

No Comments

No Known Activations