INDEX

Explanations

programming/software code

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

Pager

-0.30

ion

-0.28

 dominance

-0.27

 tabs

-0.26

 Tabs

-0.26

ä¿Ŀå®ļ

-0.26

-dom

-0.26

tab

-0.26

tab

-0.25

dee

-0.25

POSITIVE LOGITS

åĲ¬ä¼Ĺ

0.28

æĸ½

0.28

å¤§ä¼Ĺ

0.27

·¨

0.26

åıĹä¼Ĺ

0.26

ering

0.25

çĤ¹æ»´

0.25

 audience

0.25

èĮķ

0.25

á»§

0.24

Activations Density 1.641%

programming/software code

No Comments

No Known Activations