© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 614
    Prev
    Next
    INDEX
    Explanations

    say two-letter codes

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

    No Comments

    Negative Logits
    雒
    -17.38
     Buenos
    -16.25
    悉尼
    -15.69
     Mumbai
    -15.44
    上海
    -15.13
     Pune
    -14.88
    上海市
    -13.94
    笮
    -13.94
    贵阳
    -13.88
     Mediterr
    -13.81
    POSITIVE LOGITS
     AK
    50.75
     CK
    50.50
    TK
    50.25
     VK
    48.50
     FK
    48.25
    DK
    48.00
     TK
    48.00
     DK
    47.75
    VK
    47.75
    CK
    47.50
    Activations Density 0.298%

    No Known Activations