INDEX

Explanations

magnetic

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UPPORT

-0.32

pod

-0.31

Pod

-0.29

æĶ¹éĿ©

-0.29

upport

-0.29

Õ·

-0.28

æĶ¯æĮģ

-0.28

 circle

-0.27

Pod

-0.27

å°ģ

-0.27

POSITIVE LOGITS

exter

0.27

glob

0.26

isse

0.25

 regul

0.25

åĩĢåĢ¼

0.25

èĢģé¾Ħ

0.24

 medic

0.24

 acted

0.24

åŃĺéĩı

0.24

è¯ŀ

0.24

Activations Density 0.065%

magnetic

No Comments

No Known Activations