INDEX

Explanations

web scraped data

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

esub

-0.32

èĢĻ

-0.28

hyp

-0.28

 slicing

-0.27

slice

-0.27

æĳ©

-0.26

hyp

-0.26

 pinned

-0.25

_slices

-0.25

slope

-0.25

POSITIVE LOGITS

Fant

0.29

 Lomb

0.26

persona

0.25

 Fant

0.24

 Cone

0.24

»¿

0.24

æı¡æīĭ

0.24

çļĦæķħäºĭ

0.24

-led

0.24

åıį

0.23

Activations Density 0.958%

web scraped data

No Comments

No Known Activations