INDEX

Explanations

Dayton

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

æł¡

-0.29

 Reyn

-0.29

omen

-0.28

/;↵

-0.28

onen

-0.27

Ð¾Ð±ÑĢÐ°

-0.26

Ĭ¶

-0.26

itech

-0.25

éļĻ

-0.25

éĢĢå½¹

-0.24

POSITIVE LOGITS

 Great

0.27

Ð¸Ð´ÐµÐ½ÑĤ

0.26

 doubling

0.25

eam

0.25

åıĮ

0.24

ARTH

0.24

çķ¿

0.24

ç©¿éĢı

0.24

ico

0.24

MISSION

0.24

Activations Density 0.505%

Dayton

No Comments

No Known Activations