INDEX

Explanations

Code and technical reports

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

*/)↵

-0.26

 Credential

-0.25

LCD

-0.25

\DependencyInjection

-0.24

Wheel

-0.23

*/)

-0.23

-Owned

-0.23

adows

-0.23

éļıæĹ¶éļı

-0.23

 Wheel

-0.23

POSITIVE LOGITS

Ans

0.29

æĬĵå¥½

0.28

åķ¤éħĴ

0.27

å¥½äºº

0.26

Ans

0.25

åı¸ä»¤

0.25

è®°

0.24

amil

0.24

æĬĵä½ı

0.24

æĬ¬å¤´

0.24

Activations Density 0.018%

Code and technical reports

No Known Activations