Ashish, please change some codes.
leNet = NetChain[block1,
"Output" -> NetDecoder[{"Class", {0, 1, 2, 3, 4, 5, 6, 7, 8, 9}}],
"Input" -> NetEncoder[{"Image", {28, 28}, "Grayscale"}]]
weights = NetExtract[trainedNet, {1, "Weights"}];
You can visualize weights of conv1(Layer 1).
ImageAdjust[Image[#, Interleaving -> False]] & /@ weights