INDEX

Explanations

numbers

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PropertyChanged

-0.29

æŀ¶åŃĲ

-0.26

ipop

-0.25

pon

-0.25

äº¤éĢļæŀ¢çº½

-0.24

æ¯³

-0.24

 asserted

-0.24

 lighten

-0.24

pon

-0.24

issing

-0.24

POSITIVE LOGITS

çłº

0.30

ä»ģ

0.29

èĩªæĪĳ

0.28

 tear

0.27

:checked

0.27

å®ĿçŁ³

0.26

æĿı

0.25

:variables

0.25

-going

0.25

$__

0.25

Activations Density 0.006%

numbers

No Comments

No Known Activations