INDEX

Explanations

from

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

 recurrence

-0.29

ud

-0.26

Mi

-0.25

 NEXT

-0.25

ani

-0.25

DMI

-0.25

ilated

-0.25

nd

-0.24

sw

-0.24

çļĦå§¿æĢģ

-0.24

POSITIVE LOGITS

èµħ

0.27

atures

0.27

ç²¾

0.26

ç²¾åįİ

0.26

ATAR

0.26

markup

0.26

HashCode

0.25

ï¸µ

0.25

ä¼ĺçĤ¹

0.25

 Names

0.24

Activations Density 1.220%

from

No Comments

No Known Activations