INDEX

Explanations

differential equation

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

 pers

-0.29

ä¸¤çº§

-0.29

 capacity

-0.28

 capacities

-0.28

rat

-0.28

 Capacity

-0.27

å®¹éĩı

-0.27

 focused

-0.26

egg

-0.25

abble

-0.25

POSITIVE LOGITS

à¹Ĥà¸Ļ

0.29

 Stoke

0.29

IClient

0.27

 Clair

0.24

å°¼æĸ¯

0.24

asz

0.24

physics

0.23

ä¸įè¿ľ

0.23

 wisely

0.23

NRA

0.23

Activations Density 0.037%

differential equation

No Comments

No Known Activations