BACKGROUND: Differences in sensory processing are a defining characteristic of autism, affecting up to 87% of autistic individuals. These differences cause widespread perceptual changes that can negatively impact cognition, development, and daily functioning. Our research identified 5 sensory processing phenotypes with varied behavioral presentations; however, their neural basis remains unclear. In this study, we aim to ground these sensory phenotypes in unique patterns of functional connectivity. METHODS: We analyzed data from 146 autistic participants from the POND Network (Province of Ontario Neurodevelopmental Disorders Network). We classified participants into 5 sensory phenotypes using k-means clustering of scores from the Short Sensory Profile. We computed functional connectivity matrices from functional magnetic resonance imaging data across 200 cortical and 32 subcortical regions and calculated graph-theoretical measures (betweenness centrality, strength, local efficiency, and clustering coefficient) to assess information exchange between these regions. We then trained machine learning models to use these measures to classify between all pairs of sensory phenotypes. RESULTS: Our sample was clustered into 5 sensory phenotypes. The machine learning models distinguished 7 of the 10 total pairs of sensory phenotypes using graph-theoretical measures (p < .005). Information exchange within and between the somatomotor network, orbitofrontal cortex, posterior parietal cortex, prefrontal cortex, and subcortical areas was predictive of sensory phenotype. CONCLUSIONS: Sensory phenotypes in autism correspond to differences in functional connectivity across cortical, subcortical, and network levels. These findings support the view that variability in sensory processing is reflected in measurable neural patterns and motivate continued work to refine models of sensory processing, with the goal of better understanding and capturing the heterogeneity implicit in autism.