INDEX

Explanations

given

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

anos

-0.30

 Seoul

-0.29

\|

-0.28

 Koreans

-0.28

æ·

-0.28

gee

-0.27

æĮ¯ãĤĬ

-0.25

 Gratuit

-0.25

nell

-0.24

ç»Ļå¥¹

-0.24

POSITIVE LOGITS

 circular

0.31

 signatures

0.30

 signature

0.28

åī¯ä¸»å¸Ń

0.28

 convers

0.26

æĮĩ

0.25

Signature

0.25

ä½Ĩä¹Ł

0.25

 comp

0.24

 implied

0.24

Activations Density 0.110%

given

No Comments

No Known Activations