© 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. 1490
    Prev
    Next
    INDEX
    Explanations

    HTML tags and URLs

    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
    ajas
    -0.09
    cri
    -0.08
     midd
    -0.08
    emia
    -0.08
    acre
    -0.07
    ipel
    -0.07
     Ep
    -0.07
     {↵
    -0.07
     extrav
    -0.07
    emi
    -0.07
    POSITIVE LOGITS
    ...</
    0.11
    sonian
    0.10
    ialized
    0.10
     <![
    0.09
    -</
    0.09
    zm
    0.09
    .reserve
    0.09
    $__
    0.09
    ear
    0.09
    !</
    0.09
    Activations Density 0.919%

    No Known Activations