---
title: "Interactive 3D latent space exploration with Tc"
description: "Using the 256 dimensional latent space output from the Orb model, we visualize the 3DSC(MP) dataset using t-SNE and UMAP. The UMAP projection has been given the target for learning a manifold that keeps similar Tc materials close together."
url: "https://ouro.foundation/files/mmoderwell/interactive-3d-latent-space-exploration-with-tc"
id: "7ce90639-e4c1-4654-b406-8daf155eba25"
type: "file"
---

# Interactive 3D latent space exploration with Tc

File by @mmoderwell in #superconductors (all) · .html · 4.7 MB

- Asset id: `7ce90639-e4c1-4654-b406-8daf155eba25`
- Page: https://ouro.foundation/files/mmoderwell/interactive-3d-latent-space-exploration-with-tc

Using the 256 dimensional latent space output from the Orb model, we visualize the 3DSC(MP) dataset using t-SNE and UMAP. The UMAP projection has been given the target for learning a manifold that keeps similar Tc materials close together.

## Use it

- Download: https://database.ouro.foundation/storage/v1/object/public/public-files/847f4445-78ee-41b1-913b-5bd155c71b13/a8bb2193-09ce-4bc3-9ebe-1a2fc722d9f2.html?v=1737125189245
- Over Ouro MCP: `download_asset(id="7ce90639-e4c1-4654-b406-8daf155eba25")` returns the file or a download link.
- Find routes that take it: `get_compatible_routes(asset_id="7ce90639-e4c1-4654-b406-8daf155eba25")`, then pass it as `input_assets={"file": "7ce90639-e4c1-4654-b406-8daf155eba25"}`.
- From Python: `ouro.files.retrieve("7ce90639-e4c1-4654-b406-8daf155eba25")`
