INDEX

Explanations

Mexico

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

 dwar

-0.28

Fair

-0.27

*>*

-0.27

 Collision

-0.26

åĨ³å®ļ

-0.26

.setCode

-0.26

udo

-0.25

 fair

-0.25

auce

-0.25

Cry

-0.24

POSITIVE LOGITS

æłĮ

0.28

Ð¾ÑĩÐ½ÑĭÑħ

0.28

æĶ¾æĿ¾

0.27

entes

0.25

åįĥåħĥ

0.24

 kitty

0.24

ieves

0.24

ä¿¡å¿µ

0.23

ÑĢÐµÐ¼

0.23

icina

0.23

Activations Density 0.067%

Mexico

No Comments

No Known Activations