© 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. 54561
    Prev
    Next
    INDEX
    Explanations

    require statements

    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
    /build
    -0.08
     rou
    -0.08
     punct
    -0.08
     erect
    -0.08
    orm
    -0.08
     Superior
    -0.08
    abis
    -0.07
    connected
    -0.07
     tal
    -0.07
     dos
    -0.07
    POSITIVE LOGITS
     suff
    0.09
     suffice
    0.09
    bett
    0.09
     swe
    0.09
     Iv
    0.08
    .iv
    0.08
    ;↵↵
    0.08
    quip
    0.08
     Ced
    0.08
    fleet
    0.08
    Activations Density 0.008%

    No Known Activations