INDEX

Explanations

in

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

TN

-0.29

ally

-0.28

ä¸įæĪĲ

-0.26

è¯·èģĶç³»

-0.26

 INTERN

-0.26

ije

-0.26

ä¸įå±ŀäºİ

-0.25

gres

-0.24

alist

-0.24

POSITIVE LOGITS

baugh

0.28

ril

0.26

mland

0.25

 Dmit

0.25

-Dec

0.24

rames

0.24

-Smith

0.24

Ð´Ð¾Ð²

0.24

Ãło

0.23

å¹¶è´Ń

0.23

Activations Density 13.711%

in

No Known Activations