INDEX

Explanations

domestic violence

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_31.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.31.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

opher

-0.30

åĲŀåĻ¬

-0.27

Fac

-0.25

.absolute

-0.25

 Houses

-0.24

.entries

-0.24

æºĲå¤´

-0.24

fds

-0.24

ÑıÐ¼Ð¸

-0.24

-Am

-0.24

POSITIVE LOGITS

ä¹Łä¸įä¼ļ

0.27

å¤§çģ«

0.26

thood

0.26

alsa

0.25

elian

0.24

åĳ½è¿Ĳ

0.24

rita

0.24

arians

0.23

ela

0.23

LP

0.23

Activations Density 0.012%

domestic violence

No Comments

No Known Activations