INDEX

Explanations

code syntax characters

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

åľ¨è¿Ļæĸ¹éĿ¢

-0.27

xab

-0.27

è°ĥæŁ¥æĺ¾ç¤º

-0.27

æ²¡æĶ¶

-0.26

rollers

-0.25

celed

-0.25

(objects

-0.25

ElementException

-0.24

åĻİ

-0.24

 policing

-0.24

POSITIVE LOGITS

ienne

0.31

essages

0.30

ipers

0.28

åŀĵ

0.28

tape

0.26

mil

0.26

æıĴåº§

0.26

uario

0.26

ilateral

0.25

åħ¬åĬ¡

0.25

Activations Density 0.081%

code syntax characters

No Comments

No Known Activations