INDEX

Explanations

professional/technical topics

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_10.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.10.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTable

-0.30

datatable

-0.27

 Neal

-0.27

ç¼º

-0.27

 datatable

-0.26

äººæ°ĳæľįåĬ¡

-0.26

æ»ŀ

-0.26

.UnitTesting

-0.26

ully

-0.25

éĿ¢çĻ½

-0.25

POSITIVE LOGITS

ChildIndex

0.26

ej

0.25

çĸ¾

0.25

ç¾Ŀ

0.25

çŁ³æĿĲ

0.25

eper

0.24

à¹ģà¸Ħ

0.24

agram

0.24

æīįçŁ¥éģĵ

0.24

ãĤ¸ãĤ§

0.24

Activations Density 0.002%

professional/technical topics

No Comments

No Known Activations