INDEX

Explanations

Code/legal disclaimers

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

{!

-0.30

outh

-0.29

æĮĩ

-0.27

orarily

-0.26

flt

-0.25

 discrim

-0.25

ulia

-0.25

erland

-0.25

è¸£

-0.24

ï¼ģ",

-0.24

POSITIVE LOGITS

åĨ·æ°´

0.29

 Cold

0.28

Counter

0.27

åįĥ

0.27

 interactions

0.27

 Counter

0.26

 Trou

0.26

ilib

0.26

Cold

0.25

å®£ä¼łæ´»åĬ¨

0.25

Activations Density 0.032%

Code/legal disclaimers

No Comments

No Known Activations