© 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. 14380
    Prev
    Next
    INDEX
    Explanations

    [manager] => [name]

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

    No Comments

    Negative Logits
    蟾
    -23.13
    樱花
    -19.50
     Huntington
    -19.50
     sdl
    -18.50
     Gutenberg
    -18.50
    柬埔寨
    -18.25
     Madden
    -18.13
    bitcoin
    -17.88
     Cincinnati
    -17.50
     banana
    -17.50
    POSITIVE LOGITS
    imb
    19.63
    厂
    18.88
    arf
    17.75
    浆
    17.00
    亏
    16.88
    勺
    16.50
    廠
    16.13
     traf
    15.94
     SqlDbType
    15.69
    /dr
    15.69
    Activations Density 1.215%

    No Known Activations