INDEX

Explanations

code symbols

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

agged

-0.26

etime

-0.26

lat

-0.26

cheon

-0.26

éĩįçĤ¹

-0.25

east

-0.25

tsy

-0.25

 foundational

-0.25

âĿĹ

-0.25

Johnny

-0.24

POSITIVE LOGITS

çļĦæĸĩåŃĹ

0.29

thane

0.26

 GlÃ¼ck

0.25

nicos

0.25

 Than

0.25

èĢĥè¯ģ

0.25

.getClassName

0.24

BackingField

0.24

åľ°éģĵ

0.24

 Kahn

0.24

Activations Density 3.343%

code symbols

No Comments

No Known Activations