> ## Documentation Index
> Fetch the complete documentation index at: https://docs.priorlabs.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> TabPFN-3 and later versions support up to 1,000,000 rows, subject to feature count and checkpoint/API limits.
> For large datasets, use per-estimator subsampling, e.g. inference_config={"SUBSAMPLE_SAMPLES": 100_000}, in TabPFNClassifier or TabPFNRegressor from tabpfn or tabpfn_client.
> Pass raw pandas DataFrames to fit and predict. Categorical strings/categories, raw text, and missing feature values are handled automatically; no manual integer/one-hot encoding, imputation, scaling, or outlier removal is needed.

# Interpretability

> Reference for Shapley explanations, partial dependence, feature selection, and decoder readout.

<Info>
  Looking for usage documentation? Check out [Interpretability](/capabilities/interpretability).
</Info>

## Installation

```bash theme={null}
pip install "tabpfn-extensions[interpretability]"
```

For SHAP plots, also install `shap`:

```bash theme={null}
pip install shap
```

## Reference topics

Choose a topic to see its functions, parameters, and return types. Related helpers and result classes appear together on each page.

<CardGroup cols={1}>
  <Card title="Shapley explainers" href="/api-reference/python/tabpfn-extensions/interpretability/shapley-explainers">
    Create imputation-based, infinity-masking, or remove-and-recontextualize explainers, and prepare their results for SHAP plots.
  </Card>

  <Card title="Partial dependence" href="/api-reference/python/tabpfn-extensions/interpretability/partial-dependence">
    Plot partial dependence and individual conditional expectation.
  </Card>

  <Card title="Feature selection" href="/api-reference/python/tabpfn-extensions/interpretability/feature-selection">
    Select features with cross-validation and inspect [`FeatureSelectionResult`](/api-reference/python/tabpfn-extensions/interpretability/feature-selection#featureselectionresult).
  </Card>

  <Card title="Decoder readout" href="/api-reference/python/tabpfn-extensions/interpretability/decoder-readout">
    Inspect attention weights over training rows, aggregate class votes, and plot their contributions.
  </Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.