INDEX

Explanations

News/report excerpts

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

çĸı

-0.30

ãĤµãĥ¼ãĥ

-0.28

issa

-0.28

 skeleton

-0.25

 loose

-0.25

odus

-0.24

 Loose

-0.24

æł¡å¤ĸ

-0.24

rement

-0.24

 consort

-0.24

POSITIVE LOGITS

ete

0.29

Ð¾ÑģÐ¾Ð±

0.29

 landing

0.25

ivirus

0.25

Clone

0.25

.cgi

0.25

åİ¥

0.24

 Robbins

0.24

rita

0.24

 Clone

0.24

Activations Density 0.003%

News/report excerpts

No Comments

No Known Activations