INDEX

Explanations

time duration

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

 mastery

-0.28

 collective

-0.27

æİĮæı¡

-0.26

 Collective

-0.24

vig

-0.24

Tonight

-0.24

çĴŀ

-0.24

plit

-0.24

åľ¨çİ°åľº

-0.23

è£±

-0.23

POSITIVE LOGITS

Ban

0.30

.ms

0.28

endregion

0.28

æı¡æīĭ

0.27

-fly

0.27

 manh

0.27

 endregion

0.26

Ð¿ÑĢÐ¾Ñģ

0.26

gle

0.26

Ban

0.26

Activations Density 0.042%

time duration

No Comments

No Known Activations