Human diseases are fundamentally multicellular in nature with many different cell types contributing to disease progression and treatment response. However, how drugs impact each cell type in a heterogeneous population remains poorly understood. Conventional drug response studies, including those using single-cell profiling based approaches, have focused on pure cell types, ignoring population-level effects. Here, we applied highly multiplexed single cell mRNA-seq to study the impact of over 500 immunomodulatory compounds on human primary blood mononuclear cells (PBMCs), a heterogenous mixture of myeloid and lymphoid immune cell-types. We profiled over one million single cells using MULTI-seq to multiplex samples and used PopAlign, a probabilistic modeling platform, to discover cell-type specific responses for each compound in the library. Our conditions include CD3/CD28 stimulation, which activates signaling interactions that unmasks a wide range of drug responses that are not observed in resting cell populations. Our results highlight cell type-specific patterns of response: while many drugs inhibit T-cell activation in a similar manner, drug impact on macrophages are diverse. By classifying cell-type specific drug response signatures across conditions, we could identify two types of immunomodulators: localized and broad regulators of immune activation. We find localized inhibitors that act specifically on macrophages, such as TLR agonists and NSAIDs which induce pro-inflammatory and apoptotic programs, respectively. Broad modulators impact more than one cell-type; they inhibit activation in T cells but can push macrophages into inflammatory (M1), non-inflammatory (monocyte-like), anti-inflammatory (M2) or drug-specific transcriptional states. For instance, while JAK inhibitors and calcineurin inhibitors shift the balance toward non-inflammatory monocytes, some VEGFR and Bcr/ABL inhibitors generate more inflammatory M1 macrophages. Our analysis also reveals novel local activity for previously poorly characterized molecules, including a myeloid-suppressing function of a group of compounds including NSAIDs and an artificial sweetener. By providing new depth and insight into how existing compounds reshape immune populations,our dataset is a promising resource for improving therapeutic strategies, especially in cancer where macrophage state (M1/M2) can advance or reverse disease progression. Our platform can be broadly applied towards understanding heterogeneous cell populations in a wide range of therapeutic and disease conditions.