INDEX

Explanations

shop

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

omen

-0.27

itchens

-0.26

fÃ¼r

-0.26

ular

-0.25

åĽŀ

-0.25

éĵ¸

-0.24

 Happiness

-0.24

è¯ģ

-0.23

ullen

-0.23

å®īå®ģ

-0.23

POSITIVE LOGITS

_PS

0.28

å¹¡

0.27

 useContext

0.27

 Ð¿Ð¾Ð´ÑĢÐ¾Ð±

0.26

è®¾è®¡æĸ¹æ¡Ī

0.26

credits

0.25

åĲ©åĴĲ

0.25

riel

0.25

éī´åĪ«

0.25

Kes

0.25

Activations Density 0.056%

shop

No Comments

No Known Activations