Modern large language model (LLM) systems frequently route inputs to specialized experts to improve accuracy, efficiency, and robustness. Routers determine which expert to activate based on the input, typically represented as a single vector. The construction of this vector limits the distinctions the router can make. Prior work rarely isolates how this vector representation affects routing behavior. We isolate the role of the representation by holding the routing pipeline fixed and vary only how this representation is formed in multilingual settings. We find that representation choice systematically reshapes the available routing partitions. In multilingual routing settings, the routers single-vector input often only encodes shallow features (language/format), resulting in domains that are organized by these features rather than by topic. To mitigate this, we introduce Funnel pooling, a lightweight trainable in-model readout that constructs the routing vector directly from token-level hidden states and does not require a separate embedding encoder. Funnel pooling reduces language and source-dataset driven clustering and results in more topic-aligned domains. Despite this shift, downstream routing performance remains competitive with introducing only a minor inference overhead.