{
  "abstract": "RSA and CKA are standard metrics for comparing neural representations across brain regions, organisms, and deep learning models. We demonstrate a fundamental weakness: these decoding-based metrics are insensitive to encoding manifold topology---the internal functional organization of a neural population. In a controlled MNIST experiment, RSA, CKA, and Procrustes $R^2$ remain statistically unchanged when encoding topology is causally manipulated via an auxiliary clustering loss, while the two model populations differ significantly in attribution patterns, weight-graph assortativity, and out-of-distribution robustness. Across biological systems and machine learning models, similar decoding behavior can arise from small, non-representative subpopulations, and alignment metrics are insensitive to encoding manifold topology even when it is fundamentally altered. These findings bear directly on mechanistic interpretability: standard alignment metrics cannot distinguish whether two networks share the same computational circuits or merely produce indistinguishable aggregate outputs. We propose encoding manifolds and Gromov-Wasserstein distance as complementary diagnostics for any decoding-based similarity claim, and provide a Neural Manifold Explorer tool at https://johannesbertram.github.io/FNN_Manifolds/index.html for further experimentation.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2605.05907",
  "author_total": 5,
  "authors": [
    {
      "name": "Johannes Bertram"
    },
    {
      "name": "Luciano Dyballa"
    },
    {
      "name": "T. Anderson Keller"
    },
    {
      "name": "Savik Kinger"
    },
    {
      "name": "Steven W. Zucker"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/a2yfvs53g0jkk.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2605.05907",
  "fulltext_url": null,
  "id": "a2yfvs53g0jkk",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2605.05907",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "q-bio.NC"
    ],
    [
      "openalex",
      "2805|Neural dynamics and brain function"
    ]
  ],
  "openalex": "W7160636447",
  "pdf_url": "https://arxiv.org/pdf/2605.05907",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-09",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/a2yfvs53g0jkk.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:28:41Z",
      "native_id": "2605.05907",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2605.05907"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.NC",
      "subfield": "neuroscience"
    }
  ],
  "title": "Decoding Alignment without Encoding Alignment: A critique of similarity analysis in neuroscience",
  "title_text": "Decoding Alignment without Encoding Alignment: A critique of similarity analysis in neuroscience",
  "type": "preprint",
  "updated_at": "2026-10-30T12:28:41Z",
  "url": "https://research.draconitic.com/paper/a2yfvs53g0jkk",
  "venue": "arXiv",
  "versions": []
}