INDEX

Explanations

nuclear

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

áº¡p

-0.32

 Burl

-0.28

 selectors

-0.25

OLER

-0.25

--č↵

-0.25

çģŃ

-0.24

 Emil

-0.24

zob

-0.24

 migrationBuilder

-0.24

å¸Ĥ

-0.23

POSITIVE LOGITS

aco

0.29

ICON

0.28

 Pandora

0.26

 Ð¿Ð¾Ð½

0.25

iska

0.25

Ã¢n

0.25

 Pill

0.24

æŀļ

0.24

endor

0.24

 ICON

0.24

Activations Density 0.008%

nuclear

No Comments

No Known Activations