feat: implement A+ automatic semantic prompt composition filtering, dynamic active feature legend, sequence-preserving mean ablation hooks, and elite alignment science hiring dashboard

feat: implement automatic semantic feature clustering composition in SAE lab

feat: upgrade mechanistic interpretability workstation to elite 10/10 research-grade

feat: add dynamic sparsity threshold control slider and raw telemetry export tool

feat: implement Dynamic Sparse Autoencoder (SAE) Latent Extractor and Live Activation Lab

feat: complete live cpu inference, research sweep, blog & production build