diff --git a/deepinfer/model_executor/models/decoder_layer.py b/deepinfer/model_executor/models/decoder_layer.py
index cb11437..3556839 100644
--- a/deepinfer/model_executor/models/decoder_layer.py
+++ b/deepinfer/model_executor/models/decoder_layer.py
@@ -146,7 +146,10 @@ class DeepseekDecoderLayer(HCLayerMixin):
                 out, overflow = neuron_regions.entry(self.mlp, "forward_capacity")(
                     hidden_states, hidden_states_bf16, input_metadata
                 )
-                hidden_states = mlp(hidden_states, hidden_states_bf16, input_metadata) if bool(overflow) else out
+                overflowed = bool(overflow)
+                if envs.DEEPINFER_NEURON_REGION_TIMING:
+                    neuron_regions.count("moe_capacity_overflow" if overflowed else "moe_capacity_ok")
+                hidden_states = mlp(hidden_states, hidden_states_bf16, input_metadata) if overflowed else out
             else:
                 hidden_states = mlp(
                     hidden_states,
diff --git a/deepinfer/neuron_ops/regions.py b/deepinfer/neuron_ops/regions.py
index a0c8520..cd5bc6d 100644
--- a/deepinfer/neuron_ops/regions.py
+++ b/deepinfer/neuron_ops/regions.py
@@ -45,6 +45,11 @@ _SYNC_EVERY = int(os.environ.get("DEEPINFER_NEURON_SYNC_EVERY", "0"))
 _CALLS = [0]
 
 
+def count(label: str) -> None:
+    """Count an event in the per-step timings (DEEPINFER_NEURON_REGION_TIMING)."""
+    _TIMES[label].append(0.0)
+
+
 def take_timings() -> dict[str, list[float]]:
     """The region timings recorded since the last call, then reset."""
     out = dict(_TIMES)