analyze: add MoE router gating/share diagnostic plots

New "model" family in the gallery: router_gating (mean soft gate weight
vs. pre-step energy, showing the router's soft decision boundaries) and
router_share_by_pdg/router_share_by_process (stacked top-1 dispatch share
by species / true physics process). Needs a live checkpoint's Router, so
it's a documented exception to the rest of the package's polars/numpy-only
contract; gracefully degrades to a placeholder for non-MoE checkpoints.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

giant/analysis/render.py

@@ -137,12 +137,89 @@ def _render_bar(r: Reduced, params: dict):
     return fig
 
 
+def _render_router_gating(r: Reduced, params: dict):
+    n_experts = r.payload["n_experts"]
+    log_x = r.payload.get("log_x", False)
+    fig, axes = ps.new_figure(
+        "slide-16x9", title=r.title, params=params, nrows=1, ncols=2, squeeze=False
+    )
+    flat = axes.ravel()
+    for ax, key in zip(flat, ("rollout", "reference")):
+        side = r.payload.get(key, {})
+        centers = np.asarray(side.get("centers", []))
+        means = np.asarray(side.get("means", []))
+        if len(centers) and means.size:
+            cum = np.zeros(len(centers))
+            for i in range(n_experts):
+                ax.fill_between(
+                    centers, cum, cum + means[:, i], alpha=0.7, label=f"expert {i}"
+                )
+                cum = cum + means[:, i]
+        if log_x:
+            ax.set_xscale("log")
+        ax.set_ylim(0, 1)
+        ax.set_title(_SERIES_LABELS[key], fontsize=8)
+        ax.set_xlabel(r.xlabel)
+    flat[0].set_ylabel("mean gate weight")
+    ps.style_legend(flat[0], title=f"{r.payload.get('router_type', '')} router")
+    return fig
+
+
+def _render_router_share(r: Reduced, params: dict):
+    categories = r.payload["categories"]
+    n_experts = r.payload["n_experts"]
+    x = np.arange(len(categories))
+    present = [k for k in ("rollout", "reference") if k in r.payload]
+    fig, axes = ps.new_figure(
+        "slide-16x9",
+        title=r.title,
+        params=params,
+        nrows=1,
+        ncols=len(present),
+        squeeze=False,
+    )
+    flat = axes.ravel()
+    for ax, key in zip(flat, present):
+        side = r.payload[key]
+        shares = np.array([side[c] for c in categories])  # (n_cat, n_experts)
+        bottom = np.zeros(len(categories))
+        for i in range(n_experts):
+            ax.bar(x, shares[:, i], bottom=bottom, label=f"expert {i}")
+            bottom += shares[:, i]
+        ax.set_xticks(x)
+        ax.set_xticklabels(categories, rotation=45, ha="right")
+        ax.set_ylim(0, 1)
+        ax.set_title(_SERIES_LABELS[key], fontsize=8)
+    flat[0].set_ylabel("share of rows dispatched to expert")
+    ps.style_legend(flat[0], title=f"{r.payload.get('router_type', '')} router")
+    return fig
+
+
+def _render_unavailable(r: Reduced, params: dict):
+    fig, ax = ps.new_figure("thesis-single", title=r.title, params=params)
+    ax.axis("off")
+    ax.text(
+        0.5,
+        0.5,
+        r.payload.get("note", "not available"),
+        ha="center",
+        va="center",
+        wrap=True,
+        fontsize=10,
+        transform=ax.transAxes,
+    )
+    return fig
+
+
 _RENDERERS = {
     "overlay_hist": _render_overlay,
     "single_hist": _render_single,
     "grouped_hist": _render_grouped,
     "profile": _render_profile,
     "bar": _render_bar,
+    "router_gating": _render_router_gating,
+    "router_share": _render_router_share,
+    "unavailable": _render_unavailable,
 }