INDEX

Explanations

account

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

 muzzle

-0.28

 +=↵

-0.27

...)↵

-0.26

ä¸ºä¸»çº¿

-0.26

arton

-0.26

æ¬ł

-0.25

à¹Ģà¸«à¸Ļ

-0.24

éĺ¶æ®µ

-0.24

æľĪèĩ³

-0.24

ufs

-0.24

POSITIVE LOGITS

abinet

0.28

Arrow

0.27

fit

0.27

.wikipedia

0.27

Pair

0.26

 Arrow

0.26

pie

0.25

ä¸įåħĭ

0.25

pair

0.25

PM

0.25

Activations Density 0.003%

account

No Comments

No Known Activations