INDEX

Explanations

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ystone

-0.26

inity

-0.25

/npm

-0.25

 sock

-0.24

cycle

-0.24

å©´

-0.24

èĭĦ

-0.24

 Whisper

-0.23

-saving

-0.23

antity

-0.23

POSITIVE LOGITS

ç¬¦

0.32

nda

0.30

æī¹

0.28

 moment

0.27

isci

0.26

Ð³ÑĢÑĥÐ·

0.26

ä¸įèµ·

0.26

urus

0.25

ä½ľä¸ļ

0.25

åĳ¨è¾¹

0.25

Activations Density 0.000%

code

No Comments

No Known Activations