For example—many DL ideas have a neurosci inspiration, which is essentially reverse engineering the brain. Then you combine that with various other knowledge to engineer some new system. But then you want to debug it—and interpretability tools are essentially debugging tools—so debugging is a form of targeted reverse engineering (figuring out how a system actually works in practice to improve it).
In reality you often use both?
For example—many DL ideas have a neurosci inspiration, which is essentially reverse engineering the brain. Then you combine that with various other knowledge to engineer some new system. But then you want to debug it—and interpretability tools are essentially debugging tools—so debugging is a form of targeted reverse engineering (figuring out how a system actually works in practice to improve it).