Latent-abundance relations for the learned representation. Contour plot of latent features (from left to right, z_M, z_α, z_C) and their corresponding chemical abundances. The scatter points represent individual data points, and the contour lines represent data density, with lighter contours indicating regions of higher density. Straight lines show linear fits to the latent-abundance relations for stars in three T_eff bins, as indicated in the legend.