© 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. 14710
    Prev
    Next
    INDEX
    Explanations

    T => T

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

    No Comments

    Negative Logits
     kol
    -21.13
    col
    -17.75
    кол
    -17.13
    kol
    -16.38
     кол
    -16.25
    IOR
    -16.13
    STEM
    -16.13
    alth
    -15.88
    リア
    -15.69
     Кол
    -15.63
    POSITIVE LOGITS
    ssi
    18.25
    ��
    17.50
    盱
    17.00
     Raymond
    16.63
    ạy
    16.38
     Rosenberg
    16.13
    rollers
    16.00
    樾
    15.88
    滚动
    15.81
     sieve
    15.44
    Activations Density 0.599%

    No Known Activations