interpolation - graphical quality evaluation

I try to compare different interpolation models quality and I'm looking for a graphical tool to do that.

Application case: I'm not familiar with intepolation using neural networks. I decide to test it on a dataset having 5 inputs for 1 output: https://archive.ics.uci.edu/ml/datasets/Airfoil+Self-Noise# And to prospect it quickly, I used Orange canvas that integrate the sklearn Multi layer perceptron. I'm surprised to see that bigger the network is, better is the result. And I would like to investigate it.

Basic metrics are MSE, RMSE, MAE, R2. But it is a too global approach. Maybe the interpolation is good on a specific range and not somewhere else, and I would like to see that. In sklearn there is also the Explained variance score metric that is close to what I'm looking for. But I was imagining a simple quality curve between estimated values vs original values. I'm certainaly missing something. That's why I need your help.

Can you share some practice, tools, or keywords to help me in visual regression quality understanding ?