INDEX

Explanations

advantage

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

 preparation

-0.28

][/

-0.27

åĩĨå¤ĩå·¥ä½ľ

-0.26

REEN

-0.25

prepare

-0.25

 Batch

-0.24

 decentral

-0.24

urement

-0.24

Ideal

-0.24

Vog

-0.24

POSITIVE LOGITS

uggest

0.28

åıĸ

0.27

 cherry

0.26

URY

0.26

ç³ĸæŀľ

0.25

ietet

0.24

extView

0.24

ä¼ļéķ¿

0.24

 prescription

0.23

cap

0.23

Activations Density 0.062%

advantage

No Comments

No Known Activations