{ "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": 86334664, "total_decisions": 202179712, "sparsity": 0.42701942319514236, "full_attention_usage": 0.5729805768048577, "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": 79160, "total_decisions": 7220704, "sparsity": 0.010962919959051085 }, "10": { "sparse_decisions": 5720, "total_decisions": 7220704, "sparsity": 0.0007921665255908565 }, "11": { "sparse_decisions": 130720, "total_decisions": 7220704, "sparsity": 0.01810349794147496 }, "12": { "sparse_decisions": 276416, "total_decisions": 7220704, "sparsity": 0.03828103187722416 }, "13": { "sparse_decisions": 1201008, "total_decisions": 7220704, "sparsity": 0.16632838016902507 }, "14": { "sparse_decisions": 3219680, "total_decisions": 7220704, "sparsity": 0.4458955802647498 }, "15": { "sparse_decisions": 5586712, "total_decisions": 7220704, "sparsity": 0.7737073836567736 }, "16": { "sparse_decisions": 3334448, "total_decisions": 7220704, "sparsity": 0.4617898753362553 }, "17": { "sparse_decisions": 5915808, "total_decisions": 7220704, "sparsity": 0.819284103045908 }, "18": { "sparse_decisions": 5246040, "total_decisions": 7220704, "sparsity": 0.7265274964878771 }, "19": { "sparse_decisions": 6154752, "total_decisions": 7220704, "sparsity": 0.852375613236604 }, "20": { "sparse_decisions": 6963304, "total_decisions": 7220704, "sparsity": 0.9643525063484114 }, "21": { "sparse_decisions": 6725584, "total_decisions": 7220704, "sparsity": 0.9314305087149397 }, "22": { "sparse_decisions": 7069864, "total_decisions": 7220704, "sparsity": 0.9791100701538243 }, "23": { "sparse_decisions": 6992128, "total_decisions": 7220704, "sparsity": 0.968344360882263 }, "24": { "sparse_decisions": 7047448, "total_decisions": 7220704, "sparsity": 0.9760056637136767 }, "25": { "sparse_decisions": 7035632, "total_decisions": 7220704, "sparsity": 0.974369258177596 }, "26": { "sparse_decisions": 6130496, "total_decisions": 7220704, "sparsity": 0.8490163839980146 }, "27": { "sparse_decisions": 7219744, "total_decisions": 7220704, "sparsity": 0.999867048974726 } }, "by_phase": { "decode": { "sparse_decisions": 1527584, "total_decisions": 2947840, "sparsity": 0.5182045158488927, "full_attention_usage": 0.4817954841511073 }, "prefill": { "sparse_decisions": 84807080, "total_decisions": 199231872, "sparsity": 0.42567024617426674, "full_attention_usage": 0.5743297538257333 } } }