INDEX

Explanations

Code and programming

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

erate

-0.32

nego

-0.27

nal

-0.25

å·®å¼ĤåĮĸ

-0.25

Adjusted

-0.24

åĳĬè¯īä»ĸ

-0.24

åľ¨æŃ¤

-0.23

NN

-0.23

çĽ¯

-0.23

CCA

-0.23

POSITIVE LOGITS

 innoc

0.25

ulin

0.25

ALTH

0.25

alth

0.25

èģĮ

0.25

 getResources

0.24

ippet

0.24

wg

0.24

åľºä¸Ĭ

0.23

 Kosten

0.23

Activations Density 1.005%

Code and programming

No Known Activations