Analysis of the dynamics (non-stationarity) of functional connectivity patterns has recently received a lot of attention in the neuroimaging community. Most analysis has been using functional magnetic resonance imaging (fMRI), partly due to the inherent technical complexity of the electro- or magnetoencephalography (EEG/MEG) signals, but EEG/MEG holds great promise in analyzing fast changes in connectivity. Here, we propose a method for dynamic connectivity analysis of EEG/MEG, combining blind source separation with dynamic connectivity analysis in a single probabilistic model. Blind source separation is extremely useful for interpretation of the connectivity changes, and also enables rejection of artifacts. Dynamic connectivity analysis is performed by clustering the coactivation patterns of separated sources by modeling their variances. Experiments on resting-state EEG show that the obtained clusters correlate with physiologically meaningful quantities.