INDEX

Explanations

URLs and code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

éĽ¶

-0.29

å½Ĵ

-0.24

é£ĺ

-0.24

åīį

-0.24

nown

-0.24

ts

-0.24

-zero

-0.23

Ã¼ss

-0.23

_zero

-0.23

avi

-0.23

POSITIVE LOGITS

åĴ¦

0.27

 divorced

0.26

 playable

0.25

ä¹Łæĺ¯ä¸Ģç§į

0.25

å¯¹æłĩ

0.25

éĤ£æ¬¡

0.24

 cater

0.24

åĤĻ

0.24

 barring

0.24

mixed

0.24

Activations Density 0.439%

URLs and code

No Known Activations