© 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. 3324
    Prev
    Next
    INDEX
    Explanations

    names and emails

    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
    Lou
    -0.10
    chio
    -0.10
     Weinstein
    -0.10
    ÃŃtica
    -0.10
    stad
    -0.09
    utura
    -0.09
    ozilla
    -0.09
    =<
    -0.09
     curt
    -0.09
    ugar
    -0.09
    POSITIVE LOGITS
     spl
    0.07
    aims
    0.07
     cus
    0.07
     Lodge
    0.06
    eton
    0.06
    alic
    0.06
     inters
    0.06
    ikel
    0.06
    spl
    0.06
     entrances
    0.06
    Activations Density 0.275%

    No Known Activations