INDEX

Explanations

regulation entities

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç´Ģ

-0.28

è¿ĺæľīå¾Īå¤ļ

-0.27

 Hansen

-0.26

olut

-0.25

urm

-0.25

çļĦåĦ¿åŃĲ

-0.24

åºĶæĶ¶

-0.24

å¹´ä¸ĬåįĬå¹´

-0.24

åľ©

-0.24

 Hemisphere

-0.23

POSITIVE LOGITS

à¸ªà¸£à¸£

0.31

åħ±

0.27

ardy

0.27

iates

0.26

ght

0.26

 Ready

0.25

ellij

0.25

éĿĴ

0.25

æĴĳ

0.24

ErrMsg

0.24

Activations Density 0.001%

regulation entities

No Comments

No Known Activations