Embedding Tumbler

12,288 EMBEDDINGS · 384 DIMENSIONS · ONE RESTLESS 3-D WINDOW

dimension 1how much each of the 384 dimensions contributes to the view right nowdimension 384

Drag the sky to turn it. Hover a bright star to name it.

Tumble

What is happening

A rotating tesseract is a 4-D shape seen through a 3-D window that keeps turning. This is the same trick with 384 dimensions. The three axes you see are a small frame that drifts smoothly through the whole space and never returns to the same view.

What to watch for

Regions slide through each other and separate again. The ring of months opens into a circle, then flattens to a line. Filaments between regions swing like bridges. None of the points move. Only the viewpoint does.

The data is synthetic: nine topic regions, the filaments and bridges between them, a ring of months and an arc of temperature words, generated to behave like the output of a small sentence-embedding model and normalised to unit length. 290 points carry words; the rest stand in for unnamed passages. Real model output is noisier and less tidy. Because there is no model here, a typed query is placed from the named stars it mentions; the reranker is a toy that favours the topic most results share. Distances are measured in all 384 dimensions, so a result can look far away in the picture and still be near. The view never stops moving during a search. A new search swings the view, for a few seconds, toward the one whose first axes join the centres of the searches: clusters that still touch from there are close in the space, not only in the picture. Then the view tumbles on with the filter kept. Face the searches swings it back.