© 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. 55579
    Prev
    Next
    INDEX
    Explanations

    Cocoa framework classes

    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
     Joi
    -0.10
    imei
    -0.09
     Gow
    -0.09
    isoft
    -0.09
    -w
    -0.09
    angan
    -0.09
     Fall
    -0.08
    mi
    -0.08
    akis
    -0.08
     symp
    -0.08
    POSITIVE LOGITS
    .default
    0.14
    lein
    0.10
     default
    0.09
     defaulted
    0.09
    稿
    0.09
    default
    0.09
    anker
    0.08
    nement
    0.08
    æ
    0.08
    bj
    0.08
    Activations Density 0.001%

    No Known Activations