INDEX

Explanations

electric

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

æ¶ī

-0.28

çĦ°

-0.27

åĵģçīĮçļĦ

-0.26

çļĦçŃĶæ¡Ī

-0.26

ä¸

-0.25

 nightly

-0.24

çļĦç¡®

-0.24

è§Ĵèī²

-0.24

ë¥ĺ

-0.23

Disclaimer

-0.23

POSITIVE LOGITS

 reun

0.30

 pivot

0.28

pivot

0.27

dee

0.26

chu

0.26

 rect

0.25

à¤Ĭ

0.25

 Pivot

0.25

dee

0.25

 Noon

0.24

Activations Density 1.498%

electric

No Comments

No Known Activations