INDEX

Explanations

Code and legal documents

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 pools

-0.27

eway

-0.27

nano

-0.27

æĭīçĿĢ

-0.26

(pool

-0.26

SQLException

-0.25

quete

-0.25

antee

-0.25

 pool

-0.25

 nacional

-0.24

POSITIVE LOGITS

åºŃ

0.37

æĹ¦

0.31

 titular

0.29

åĬ³åĬ¨

0.27

kp

0.26

Ļ¨

0.25

mons

0.25

ä¸ļ

0.25

ms

0.25

MOZ

0.24

Activations Density 0.000%

Code and legal documents

No Known Activations