INDEX

Explanations

Code/technical content

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

terior

-0.30

ot

-0.26

ä½ĵéªĮ

-0.26

à¹Ģà¸«

-0.24

-and

-0.24

 ìĪĺ

-0.24

ï¼Ĩ

-0.24

amm

-0.23

usage

-0.23

QueryBuilder

-0.23

POSITIVE LOGITS

 Copp

0.33

Ð¸Ð½Ñĭ

0.26

 Goth

0.25

 vÃ¶

0.25

rou

0.25

Pow

0.25

 manh

0.24

éŁ«

0.24

.fi

0.23

æĤ¬æĮĤ

0.23

Activations Density 30.928%

Code/technical content

No Known Activations