INDEX

Explanations

Conjunctions and punctuation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fÃ¤ll

-0.28

ocop

-0.28

åħŃå¤§

-0.27

äºĮèĢħ

-0.27

å°±èĥ½

-0.25

èıĮ

-0.25

à°Ī

-0.25

clude

-0.24

åºķ

-0.24

è¿Ļåĩł

-0.24

POSITIVE LOGITS

edin

0.29

 ours

0.27

 famously

0.27

è®¤

0.26

pit

0.25

ìį¨

0.25

pit

0.25

oriously

0.25

ookies

0.24

 otherwise

0.24

Activations Density 24.669%

Conjunctions and punctuation

No Comments

No Known Activations