INDEX

Explanations

Opera

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

uras

-0.28

æīĢéľĢè¦ģçļĦ

-0.28

æĥ®

-0.27

èĳ³

-0.26

å°Ķ

-0.26

bn

-0.26

éĩįå¿ĥ

-0.25

ä¸įåĩº

-0.25

.utf

-0.24

ä¸ĢåŃĹ

-0.24

POSITIVE LOGITS

ductory

0.30

UMENT

0.28

umps

0.27

Ach

0.26

apist

0.26

ellow

0.25

çĶ³

0.25

ä¿¡çĶ¨

0.24

getRoot

0.24

umno

0.24

Activations Density 0.107%

Opera

No Comments

No Known Activations