INDEX

Explanations

of

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

(Category

-0.28

æ³ķå®ļ

-0.25

 cáº£

-0.25

éŃĦ

-0.24

è¿ĺæĺ¯å¾Ī

-0.24

 damp

-0.23

BOOK

-0.23

plot

-0.23

core

-0.23

 QString

-0.23

POSITIVE LOGITS

 independents

0.30

æĹłåħ³

0.28

undry

0.27

anon

0.26

è£¤

0.26

åĮį

0.26

à¹Īà¸Ńà¸¢

0.25

anan

0.25

æ´»åĬ¨çİ°åľº

0.25

antry

0.24

Activations Density 0.001%

of

No Comments

No Known Activations