INDEX

Explanations

text snippets/quotes

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

imos

-0.35

ä¸Ģçº§

-0.31

 entertain

-0.26

acters

-0.26

å¹¸

-0.25

fony

-0.25

ekt

-0.24

æĶ¾æīĭ

-0.24

åĩĢåĮĸ

-0.24

aland

-0.24

POSITIVE LOGITS

hack

0.30

PostBack

0.28

å¤¹

0.28

ÑħÐ¸

0.26

ignum

0.25

 pars

0.25

 HACK

0.24

atism

0.24

Hack

0.24

limits

0.24

Activations Density 0.019%

text snippets/quotes

No Comments

No Known Activations