INDEX

Explanations

computer/programming discussions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¶Ĭ

-0.25

emain

-0.24

Lv

-0.24

heard

-0.24

 Wordpress

-0.23

pei

-0.23

eo

-0.23

åħ¹

-0.23

 sÃŃ

-0.23

 mainScreen

-0.23

POSITIVE LOGITS

å¤¯å®ŀ

0.28

å·¡è§Ĩ

0.28

astery

0.28

å·¡

0.27

è¡Įèµ°

0.26

afa

0.25

Pip

0.25

tub

0.24

-progress

0.24

pip

0.24

Activations Density 0.053%

computer/programming discussions

No Comments

No Known Activations