INDEX

Explanations

Addresses

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Sapphire

-0.29

ordo

-0.28

éľľ

-0.26

å¼Ģç«¯

-0.26

æĹĹ

-0.26

hz

-0.25

çĶ£

-0.25

åħ¨éĿ¢æİ¨è¿Ľ

-0.24

vasive

-0.24

sitemap

-0.24

POSITIVE LOGITS

(Address

0.28

 Address

0.27

 configure

0.26

 addresses

0.26

 setAddress

0.25

Ram

0.25

sar

0.25

 ↵        ↵

0.25

 address

0.24

 adresse

0.24

Activations Density 0.114%

Addresses

No Comments

No Known Activations