{ "definition": "hard AHA gate zeros / all token x KV-head x layer decisions, token-weighted over prefill and decode", "router_granularity": "token", "native_router_decisions": 25272464, "effective_router_decisions": 202179712, "native_router_note": "Native decisions count learned gate logits before broadcast; effective decisions always use token x KV-head x layer for matched sparsity.", "sparse_decisions": 15539856, "total_decisions": 202179712, "sparsity": 0.07686159924889002, "full_attention_usage": 0.92313840075111, "per_layer": { "0": { "sparse_decisions": 0, "total_decisions": 7220704, "sparsity": 0.0 }, "1": { "sparse_decisions": 0, "total_decisions": 7220704, "sparsity": 0.0 }, "2": { "sparse_decisions": 0, "total_decisions": 7220704, "sparsity": 0.0 }, "3": { "sparse_decisions": 0, "total_decisions": 7220704, "sparsity": 0.0 }, "4": { "sparse_decisions": 0, "total_decisions": 7220704, "sparsity": 0.0 }, "5": { "sparse_decisions": 0, "total_decisions": 7220704, "sparsity": 0.0 }, "6": { "sparse_decisions": 0, "total_decisions": 7220704, "sparsity": 0.0 }, "7": { "sparse_decisions": 0, "total_decisions": 7220704, "sparsity": 0.0 }, "8": { "sparse_decisions": 0, "total_decisions": 7220704, "sparsity": 0.0 }, "9": { "sparse_decisions": 0, "total_decisions": 7220704, "sparsity": 0.0 }, "10": { "sparse_decisions": 0, "total_decisions": 7220704, "sparsity": 0.0 }, "11": { "sparse_decisions": 0, "total_decisions": 7220704, "sparsity": 0.0 }, "12": { "sparse_decisions": 0, "total_decisions": 7220704, "sparsity": 0.0 }, "13": { "sparse_decisions": 432, "total_decisions": 7220704, "sparsity": 5.982796137329546e-05 }, "14": { "sparse_decisions": 3544, "total_decisions": 7220704, "sparsity": 0.000490810868303146 }, "15": { "sparse_decisions": 378032, "total_decisions": 7220704, "sparsity": 0.05235389790247599 }, "16": { "sparse_decisions": 1952, "total_decisions": 7220704, "sparsity": 0.00027033375139044616 }, "17": { "sparse_decisions": 131768, "total_decisions": 7220704, "sparsity": 0.01824863614406573 }, "18": { "sparse_decisions": 33576, "total_decisions": 7220704, "sparsity": 0.004649962108957797 }, "19": { "sparse_decisions": 64112, "total_decisions": 7220704, "sparsity": 0.008878912637881292 }, "20": { "sparse_decisions": 123288, "total_decisions": 7220704, "sparsity": 0.017074235420812153 }, "21": { "sparse_decisions": 287688, "total_decisions": 7220704, "sparsity": 0.039842098498982924 }, "22": { "sparse_decisions": 1334864, "total_decisions": 7220704, "sparsity": 0.18486618479306172 }, "23": { "sparse_decisions": 3498784, "total_decisions": 7220704, "sparsity": 0.48454887501274113 }, "24": { "sparse_decisions": 1545728, "total_decisions": 7220704, "sparsity": 0.2140688774944936 }, "25": { "sparse_decisions": 860456, "total_decisions": 7220704, "sparsity": 0.11916511187828777 }, "26": { "sparse_decisions": 56296, "total_decisions": 7220704, "sparsity": 0.007796469707108892 }, "27": { "sparse_decisions": 7219336, "total_decisions": 7220704, "sparsity": 0.9998105447889846 } }, "by_phase": { "decode": { "sparse_decisions": 270424, "total_decisions": 2947840, "sparsity": 0.09173632218844985, "full_attention_usage": 0.9082636778115502 }, "prefill": { "sparse_decisions": 15269432, "total_decisions": 199231872, "sparsity": 0.07664151245840826, "full_attention_usage": 0.9233584875415918 } } }