INDEX

Explanations

cause

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

ÐµÑĢÑĮ

-0.30

kaar

-0.27

åįİçĽĽé¡¿

-0.27

 Verizon

-0.26

stitial

-0.25

Washington

-0.24

åħļæĶ¿

-0.24

æĶ¯æŁ±

-0.24

éĤ£åĦ¿

-0.24

åħ¨å¤©

-0.24

POSITIVE LOGITS

éĻĲåº¦

0.30

åºķ

0.29

etter

0.28

åĬ

0.27

 constructive

0.27

éľ²

0.26

 gran

0.25

lice

0.25

 amplify

0.25

ipped

0.24

Activations Density 0.083%

cause

No Comments

No Known Activations