Embedding Similarity Explorer
Cosine similarity between two pasted number vectors.
Runs in your browser. Nothing is uploaded — your input is processed on this device and discarded when you close the tab.
Embedding Similarity Explorer
This tool works on numbers you paste. It does not create embeddings and does not call any embedding service.
How to use this tool
- Paste the first vector of numbers.
- Paste a second vector of the same length.
- Press Generate for the cosine similarity: 1 means the same direction, 0 means unrelated, -1 means opposite.
Worked example
For the vectors [1, 2, 3] and [1, 2, 3], the cosine similarity is 1, because the two vectors point in exactly the same direction. For [1, 0] and [0, 1] it is 0.
What this tool does not do / Limits
This tool computes cosine similarity from numbers you paste only. It does NOT create embeddings, does not call any model or API, and cannot turn text into vectors for you.
Frequently asked questions
Why must both vectors have the same length?
Cosine similarity compares matching positions one by one, so vectors of different lengths cannot be compared this way.
What does a score near 0 mean?
It means the vectors point in unrelated directions. It does not by itself prove two texts are unrelated, since the result depends on the numbers supplied.
Related tools
JSON Studio
Format, validate, minify, query and compare JSON in your browser, with precise line-and-column errors.
LiveRegex Tester
Test patterns against sample text with match highlighting, capture groups and a safe one-second timeout.
LiveSecurity Header and DNS Checker
Check HSTS, CSP and other security headers, TLS details, and DNS/email authentication records (SPF, DKIM, DMARC).
Live