INDEX

Explanations

Units of measure

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

 ↵↵

-0.24

 chÃŃnh

-0.24

 Lesson

-0.24

 waters

-0.24

↵↵

-0.23

èĤłéģĵ

-0.23

FAT

-0.23

 reached

-0.23

OW

-0.23

å¼ĢäºĨ

-0.23

POSITIVE LOGITS

bish

0.28

ammable

0.28

 Reserved

0.26

reserved

0.25

guarded

0.25

 reservation

0.25

reservation

0.24

reserve

0.24

-scalable

0.24

uously

0.24

Activations Density 1.410%

Units of measure

No Comments

No Known Activations