INDEX

Explanations

ao

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

Listener

-0.32

è®¤

-0.28

car

-0.26

 cooler

-0.25

 naturally

-0.24

uen

-0.24

isten

-0.24

vell

-0.24

æĿĲæĸĻ

-0.23

ist

-0.23

POSITIVE LOGITS

orest

0.27

zers

0.26

é³ı

0.26

á»§y

0.25

æģ¼

0.25

çĦķ

0.25

.YesNo

0.25

ä¼ĳãģ¿

0.25

atial

0.24

andon

0.24

Activations Density 0.784%

ao

No Comments

No Known Activations