INDEX

Explanations

Removal

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

rix

-0.31

rez

-0.27

 tome

-0.26

åµ¬

-0.26

ÄĨ

-0.26

Cre

-0.25

_HW

-0.25

 ring

-0.25

tober

-0.25

iesel

-0.25

POSITIVE LOGITS

erv

0.30

 Towers

0.29

åĬ¨éĿĻ

0.28

 crude

0.27

åħ¶éĹ´

0.26

 Separ

0.26

 menn

0.25

æįİ

0.25

 Secure

0.25

ç²Ĺ

0.25

Activations Density 0.005%

Removal

No Comments

No Known Activations