© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8848
    Prev
    Next
    INDEX
    Explanations

    key-value pair, TimeField, ball pivot

    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
    Negative Logits
    ures
    -0.10
     Watt
    -0.09
    алÑĮ
    -0.08
     parameters
    -0.07
    erre
    -0.07
    atat
    -0.07
    unu
    -0.07
    urch
    -0.07
     rapport
    -0.07
    apro
    -0.07
    POSITIVE LOGITS
    ioso
    0.11
     Fare
    0.09
    quier
    0.09
    à¸ĸ
    0.09
    akis
    0.09
    otherwise
    0.08
    -headed
    0.08
     slee
    0.08
     otherwise
    0.08
     Bios
    0.08
    Activations Density 0.766%

    No Known Activations