INDEX

Explanations

nobility, titles, historical figures

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

ulos

-0.29

 incidental

-0.26

ä¼ĺ

-0.25

ì§Ĳ

-0.25

 Bair

-0.24

è²Į

-0.24

 Balanced

-0.24

voir

-0.24

æ³¥

-0.23

icer

-0.23

POSITIVE LOGITS

 repe

0.31

æ¡Ĩæŀ¶

0.30

framework

0.29

èĪ¸

0.26

.addColumn

0.25

:min

0.25

oton

0.25

aways

0.25

 minut

0.25

åķ¶

0.24

Activations Density 0.002%

nobility, titles, historical figures

No Comments

No Known Activations