exege
Tools for understanding and evaluating scientific machine-learning models: what an emulator holds inside, sparse autoencoders trained on it, figures, and a local app over them. The name comes from the Greek stem exēgē-, associated with explanation and interpretation.
Research tool.
exegeis early. What is described here works; expect it to change.
$ pip install exege # everything but torch
$ pip install 'exege[nn]' # and torch, for training sparse autoencoders
$ exege --help
This is the full install. It holds no code of its own: it installs
exege-core with every extra but nn, and both
provide the same import exege and the same exege command. For the light install,
Click only, with each subpackage's dependencies added as you need them:
$ pip install 'exege-core[latents]'
- Documentation: https://exege.readthedocs.io
- Source and issues: https://github.com/mahf708/exege
MIT.
1 maintainer
Metadata
1 maintainer
Release files for exege 0.7.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| exege-0.7.0.tar.gz | 1.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| exege-0.7.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 3.5 kB
Release files / exege-0.7.0.tar.gz
| Download URL | exege-0.7.0.tar.gz |
|---|---|
| Size | 1.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
bb0d2d95b3580ff11a127c9f8fa7ce228aa617e0a500f82c9f5cbc932a614d43
|
|
BLAKE2b-256 checksum How to use checksums |
f5662517004e97d0ce36d3126032f404feb7b74cd2adc2edcbc5b6b91d88e595
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 9, 2026.
Transparency logRelease files / exege-0.7.0-py3-none-any.whl
| Download URL | exege-0.7.0-py3-none-any.whl |
|---|---|
| Size | 1.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e6027eb13f4d970c4f375e48f891cbc3ecc7129e829ade3ad5e56abff69b040a
|
|
BLAKE2b-256 checksum How to use checksums |
40587b90434c1a5037e365d29941c75b3b83f869442a8f2341bc5f3475e34ae3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 9, 2026.
Transparency log
