INDEX

Explanations

people

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

 balancing

-0.29

å¹³è¡¡

-0.28

 balance

-0.27

balance

-0.26

åĩ¼

-0.26

 Balance

-0.25

SHOP

-0.25

çıŃè½¦

-0.24

Convention

-0.24

èĦĳ

-0.24

POSITIVE LOGITS

 infring

0.29

quia

0.29

 chÃŃ

0.28

emade

0.27

 Analyst

0.27

&D

0.26

 bied

0.25

 Isles

0.25

owered

0.24

éĩįè§Ĩ

0.24

Activations Density 0.820%

people

No Comments

No Known Activations