Skip to main content

Trendscape — Concept Exploration on Latent Spaces

About #

Trendscape is a toolkit for exploring inter-concept relationships on language model latent spaces. Natural language inputs are mapped to embedding spaces where neighbor graphs are constructed, and path discovery across these graphs reveals how concepts relate and connect. Verified with Word2Vec (chiVe) on literary works and Sparse AutoEncoder (SAE) features from LLM internals.

Presentations #
  • YANS 2024 [S5-P02] — 単語分散表現モデルの埋め込み空間を用いた概念間探索手法の構築と大規模言語モデルの機械論的解釈可能性への応用
  • NLP 2025 [P2-25] — Trendscape 1.0: 言語モデルの潜在空間上の概念探索
Tech Stack #

Python, Sentence-Transformers, Polars, marimo, Plotly

See Also #
Junya G. Honda
Author
Junya G. Honda
Master’s student in Computer Science and Engineering at Toyohashi University of Technology (Uehara Lab). Interested in how AI can bring new insights to neuroscience — analyzing brain networks as graphs with GNNs, and using counterfactual explanations to turn model predictions into actionable insights for clinical use. Also exploring how to extract and visualize the knowledge that AI models acquire internally.