© 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. 54079
    Prev
    Next
    INDEX
    Explanations

    amounts of money and quantities

    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
    hus
    -0.07
    fd
    -0.07
     max
    -0.07
    기
    -0.07
     Bu
    -0.06
     des
    -0.06
    max
    -0.06
    erek
    -0.06
    ukt
    -0.06
    ula
    -0.06
    POSITIVE LOGITS
     hugely
    0.11
     millions
    0.10
     Huge
    0.10
    enan
    0.10
    oard
    0.10
    gaard
    0.10
     Millions
    0.10
    avn
    0.10
    ]._
    0.10
    pects
    0.09
    Activations Density 0.044%

    No Known Activations