© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 58442
    Prev
    Next
    INDEX
    Explanations

    Mario, plane, machines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ll
    -0.09
     TE
    -0.08
    TE
    -0.08
    (dot
    -0.08
     Seventh
    -0.08
    ا
    -0.08
    ::
    -0.07
    ill
    -0.07
     oral
    -0.07
    anza
    -0.07
    POSITIVE LOGITS
     Kend
    0.11
    ...↵↵↵
    0.09
    _WM
    0.09
    bang
    0.09
    iku
    0.09
    .Metro
    0.09
    .${
    0.09
    uckets
    0.09
     Marathon
    0.08
    LC
    0.08
    Activations Density 0.350%

    No Known Activations