© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14844
    Prev
    Next
    INDEX
    Explanations

    public attention

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

    No Comments

    Negative Logits
     Sith
    -16.50
     insol
    -16.25
    信息服务
    -16.13
     repo
    -15.88
     repositories
    -15.81
    Repositories
    -15.13
    maintenance
    -14.94
    胤
    -14.75
    ereg
    -14.56
    信息系统
    -14.56
    POSITIVE LOGITS
    热议
    23.25
    热潮
    19.25
    热度
    19.00
    关注
    19.00
     heat
    18.88
    热点
    18.75
    讨论
    18.50
    沸腾
    18.38
    热
    17.38
     Heat
    17.25
    Activations Density 0.230%

    No Known Activations