© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15648
    Prev
    Next
    INDEX
    Explanations

    [出] => [一]

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

    No Comments

    Negative Logits
     Serge
    -19.00
     Laurie
    -18.50
     Netflix
    -17.38
    保姆
    -17.00
     spam
    -17.00
     serge
    -16.88
    旺季
    -16.75
    谗
    -16.75
     spoil
    -16.50
     preempt
    -16.38
    POSITIVE LOGITS
    phin
    19.38
    犍
    17.38
     getImage
    16.88
    PELL
    16.75
    APH
    16.63
    IPH
    16.38
    hausen
    15.94
    ibs
    15.94
     Sphinx
    15.94
    phy
    15.88
    Activations Density 0.382%

    No Known Activations