INDEX

Explanations

technical code and documentation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TestId

-0.27

 trophy

-0.27

emarks

-0.26

å»¶

-0.25

ensibly

-0.24

bane

-0.24

èĥĮçĿĢ

-0.24

 stdin

-0.24

amen

-0.24

dings

-0.24

POSITIVE LOGITS

 using

0.34

 utilizando

0.30

 optimized

0.29

 utilizing

0.28

 Using

0.28

æ¯Ķäºļ

0.28

_using

0.28

	using

0.28

å®ŀæĸ½

0.27

formik

0.27

Activations Density 0.028%

technical code and documentation

No Comments

No Known Activations