© 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. 54340
    Prev
    Next
    INDEX
    Explanations

    sports teams and scores

    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
    uum
    -0.09
     presenter
    -0.09
    adesh
    -0.09
     minib
    -0.08
    olk
    -0.08
    played
    -0.08
     denial
    -0.08
    lag
    -0.08
     adm
    -0.08
     Trouble
    -0.08
    POSITIVE LOGITS
    ones
    0.09
    nee
    0.08
     Lis
    0.08
    sey
    0.08
    idy
    0.08
    unction
    0.08
    eres
    0.08
    rei
    0.08
    é£
    0.08
    Transaction
    0.07
    Activations Density 0.030%

    No Known Activations