© 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. 16313
    Prev
    Next
    INDEX
    Explanations

    of course

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

    No Comments

    Negative Logits
    昇
    -19.38
    升
    -17.75
    桥
    -17.38
    橋
    -16.25
    跪
    -16.00
    blink
    -15.00
    镶
    -14.94
     PIX
    -14.75
    镒
    -14.69
    bling
    -14.56
    POSITIVE LOGITS
    cour
    21.88
    course
    21.50
     Corey
    21.00
     cou
    20.75
    reon
    20.38
     Cour
    20.38
    cou
    20.00
    コー�
    19.88
     cors
    19.63
    Cole
    19.63
    Activations Density 0.012%

    No Known Activations