INDEX

Explanations

Ordinal numbers

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

perature

-0.29

osaur

-0.27

 rigorous

-0.25

.toBe

-0.24

 Massive

-0.24

ENT

-0.24

 braces

-0.24

æľ¬ç½ĳ

-0.23

optim

-0.23

othermal

-0.23

POSITIVE LOGITS

anan

0.29

èĦ±

0.26

åĳ½

0.26

æķ´ä½ĵ

0.25

èĲ½å®ŀ

0.25

åĮ¹

0.25

æģ¯æģ¯

0.25

lobs

0.24

é¼¬

0.24

straint

0.24

Activations Density 38.604%

Ordinal numbers

No Comments

No Known Activations