© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1127
    Prev
    Next
    INDEX
    Explanations

    [军] => [阀]

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

    No Comments

    Negative Logits
     Musk
    -16.25
     tokens
    -15.44
     script
    -15.38
    宫
    -15.13
     Tokens
    -15.00
    getToken
    -14.88
    游戏
    -14.69
     Numer
    -14.56
     numer
    -14.50
    /token
    -14.44
    POSITIVE LOGITS
     style
    34.25
     statistics
    31.63
     styles
    31.50
    statistics
    30.63
     Statistics
    30.25
     Style
    30.25
    风格
    30.13
     statistical
    29.75
    style
    29.63
    统计
    29.13
    Activations Density 0.349%

    No Known Activations