Skip to main content

Topics Community

Menu

Topics Community My Profile

RNN

Interactive Lesson

Concepts & intuition

Inside the Model

Weights, matrices & math

Implementation walkthrough

Guided experiments & ablations

Test your understanding

Discuss & ask questions

quantml.org

QuantML
Topics

Dynamical SystemsVisualizations

RNN

Inside the Model

Explore hidden state trajectories, gradient flow through time, eigenvalue spectra, and how individual neurons specialize. Inspect every parameter at every training step.

Inside the RNN visualizes a trained character-level RNN with real data. You can explore hidden state trajectories projected into PCA space, trace gradient flow through time to see vanishing effects, inspect the eigenvalue spectrum and spectral radius evolution, and observe how Elman-style categories emerge from prediction patterns. Memory diagnostics and weight norm evolution are also available.