© 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. 61802
    Prev
    Next
    INDEX
    Explanations

    Santa followed by names or places

    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
    ful
    -0.12
    ingly
    -0.11
    able
    -0.09
     Hä
    -0.08
     hä
    -0.07
    ison
    -0.07
     resultant
    -0.07
    ITIONS
    -0.07
    rij
    -0.07
    eon
    -0.07
    POSITIVE LOGITS
    ropp
    0.10
     ruins
    0.10
    ruz
    0.09
    cies
    0.09
    linger
    0.09
    tu
    0.09
     Jay
    0.09
    dt
    0.09
    tan
    0.09
    tics
    0.09
    Activations Density 0.003%

    No Known Activations