INDEX

Explanations

energy

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

æĺİæĹ¥

-0.27

 Osman

-0.26

ernes

-0.25

oday

-0.24

gratis

-0.24

ijn

-0.24

ungan

-0.23

usalem

-0.23

plate

-0.23

è§ĦçŁ©

-0.23

POSITIVE LOGITS

_power

0.29

power

0.28

 Powered

0.27

Power

0.27

cycl

0.27

Powered

0.26

åĬŁçİĩ

0.26

rac

0.26

æĿĥåĬĽ

0.25

 Power

0.25

Activations Density 0.010%

energy

No Comments

No Known Activations