INDEX

Explanations

rot

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

ester

-0.26

applications

-0.26

 wholes

-0.26

 Whole

-0.26

Whole

-0.25

tools

-0.25

é«ĺå±±

-0.24

bsites

-0.24

 Fuller

-0.24

 mand

-0.24

POSITIVE LOGITS

æģ¶åĮĸ

0.28

æĦıåĳ³

0.28

-che

0.27

beg

0.26

å¼ĳ

0.25

 Quotes

0.24

åĳĽ

0.24

keh

0.24

ä»Ģä¹ĪæĦıæĢĿ

0.24

che

0.24

Activations Density 0.211%

rot

No Comments

No Known Activations