INDEX

Explanations

names and companies

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

Ð±Ð»Ð¾Ðº

-0.27

 Balk

-0.26

ä¹ŁæĹłæ³ķ

-0.26

xl

-0.25

oub

-0.25

çħ§

-0.25

è¿ĺæĺ¯

-0.24

xl

-0.24

æĪĳè¿ĺæĺ¯

-0.24

å¹´éĻĲ

-0.23

POSITIVE LOGITS

iland

0.30

 operands

0.26

agi

0.26

ierce

0.25

 chimpan

0.25

ospace

0.24

\""

0.24

(['/

0.23

æīĭèīº

0.23

 legit

0.23

Activations Density 0.009%

names and companies

No Comments

No Known Activations