INDEX

Explanations

tire

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

 grat

-0.31

ifestyles

-0.29

åķĨæĬ¥

-0.28

emie

-0.26

ellas

-0.26

SizeMode

-0.26

ivist

-0.25

ickness

-0.25

ëĿ¼ëıĦ

-0.25

ä¸įçĦ¶

-0.24

POSITIVE LOGITS

break

0.34

æĿĥ

0.31

odel

0.31

ble

0.28

 historically

0.27

ppe

0.27

éĺ²

0.26

 responsibility

0.25

Band

0.25

ä¸ĭéĿ¢

0.25

Activations Density 6.628%

tire

No Comments

No Known Activations