INDEX

Explanations

paper

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 setResult

-0.29

noÅĽci

-0.27

aturing

-0.25

 likely

-0.25

ä¸Ĭæľī

-0.25

èĵĳ

-0.25

omba

-0.24

ìľ¡

-0.24

angler

-0.24

acciÃ³n

-0.24

POSITIVE LOGITS

 vide

0.31

iya

0.27

æĬķ

0.27

éĻ¤éĿŀ

0.27

é¼ĵ

0.26

æĬ¥

0.25

 toch

0.25

ificates

0.25

 verses

0.24

èĬ¬åħ°

0.24

Activations Density 0.001%

paper

No Comments

No Known Activations