We propose methods for the analysis of hierarchical clustering that fully use\nthe multi-resolution structure provided by a dendrogram. Specifically, we\npropose a loss for choosing between clustering methods, a feature importance\nscore and a graphical tool for visualizing the segmentation of features in a\ndendrogram. Current approaches to these tasks lead to loss of information since\nthey require the user to generate a single partition of the instances by\ncutting the dendrogram at a specified level. Our proposed methods, instead, use\nthe full structure of the dendrogram. The key insight behind the proposed\nmethods is to view a dendrogram as a phylogeny. This analogy permits the\nassignment of a feature value to each internal node of a tree through an\nevolutionary model. Real and simulated datasets provide evidence that our\nproposed framework has desirable outcomes and gives more insights than\nstate-of-art approaches. We provide an R package that implements our methods.\n