INDEX

Explanations

data storage/computer systems

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

æ½¦

-0.32

 plotting

-0.27

Å°

-0.26

iances

-0.25

@endif

-0.24

 cÃ¡

-0.24

æĮ¥

-0.24

æĹıç¾¤

-0.24

%%%

-0.24

 Year

-0.23

POSITIVE LOGITS

pul

0.29

Pul

0.28

Kul

0.28

è¢ĸ

0.28

><![

0.28

æī£

0.27

 nháºŃp

0.25

 viá»ĩn

0.25

Ð¾ÑģÑĤÐ¾Ñı

0.25

so

0.24

Activations Density 0.023%

data storage/computer systems

No Comments

No Known Activations