© 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. 1452
    Prev
    Next
    INDEX
    Explanations

    sports events and conditions

    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
    /drivers
    -0.10
    :host
    -0.09
    Ł¥
    -0.09
     RAT
    -0.09
    charg
    -0.09
    conds
    -0.09
     grues
    -0.09
     _(
    -0.09
    TextColor
    -0.08
    .fm
    -0.08
    POSITIVE LOGITS
     japan
    0.07
    ssid
    0.06
    goto
    0.06
    olla
    0.06
    _HERSHEY
    0.06
     overhead
    0.06
     Cock
    0.06
    ĵåIJį
    0.06
     emiss
    0.06
    dbName
    0.06
    Activations Density 5.099%

    No Known Activations