© 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. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14459
    Prev
    Next
    INDEX
    Explanations

    Mary

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ssi
    -19.00
    ��
    -18.25
    rollers
    -17.00
    滚动
    -16.88
    盱
    -16.50
     Rolling
    -16.38
    ạy
    -16.13
     Rosenberg
    -15.94
    樾
    -15.81
     sieve
    -15.63
    POSITIVE LOGITS
     kol
    21.13
    кол
    17.00
    col
    16.88
    IOR
    16.75
     кол
    16.13
    kol
    15.94
    リア
    15.63
     ephem
    15.31
    alth
    15.06
     Кол
    14.94
    Activations Density 0.735%

    No Known Activations