INDEX

Explanations

Code and technical writing

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

Not in Any Lists

No Comments

Negative Logits

essor

-0.31

çļĦäººæĿ¥è¯´

-0.28

iele

-0.27

anse

-0.26

 estimates

-0.26

placements

-0.26

å¡Ĭ

-0.26

 guessing

-0.25

ental

-0.25

 Estimates

-0.25

POSITIVE LOGITS

ä¸»åĬ¨

0.31

ä½ľä¸º

0.29

 notation

0.26

awn

0.26

åĲįä¹ī

0.25

 heck

0.25

è¯´è¯Ŀ

0.24

ÉĲ

0.23

æĸ°å¸¸æĢģ

0.23

ä¸»åĭķ

0.23

Activations Density 55.436%

Code and technical writing

No Comments

No Known Activations