We present a tool for the interactive exploration and analysis of large clustered graphs. The tool empowers users to control the granularity of the graph, either by direct interaction (collapsing/expanding clusters) or via a slider that automatically computes a clustered graph of the desired size. Moreover, we explore the use of learning algorithms to capture graph exploration preferences based on a history of user interactions. The learned parameters are then used to modify the action of the slider in view of mimicking the natural interaction/exploration behavior of the user.