We present an interactive visualization tool to explore high-dimensional features of audiovisual data extracted from a video archive of live music performances. Our tool presents overviews of data features, similarities between song recordings, and details of the extracted visual and audio features. Features are extracted using neural networks, signal processing techniques, and audio analysis tools. Furthermore, we present a similarity metric to measure how different relevant recordings are compared to other videos. We illustrate our approach via use cases showing initial results to analyze song features, compare songs, identify outstanding songs, and detect song clusters.