INDEX

Explanations

quotation marks

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

æĸĩä¹¦

-0.28

gis

-0.26

¡°

-0.25

ç»Łè®¡

-0.25

 wire

-0.25

appiness

-0.24

orgh

-0.24

lider

-0.24

';";↵

-0.24

adar

-0.24

POSITIVE LOGITS

ä¸įåİ»

0.31

è¹Ī

0.27

letes

0.26

,,,

0.26

fle

0.26

LETE

0.26

æ¶¯

0.25

åĲ²

0.25

æľŁæľ«

0.24

å¤§å¤§

0.24

Activations Density 0.002%

quotation marks

No Comments

No Known Activations