© 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. 14272
    Prev
    Next
    INDEX
    Explanations

    say "sub"

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

    No Comments

    Negative Logits
     function
    -25.38
     implementation
    -24.50
    函数
    -23.38
     functions
    -23.38
    -function
    -23.13
    implementation
    -22.88
    functions
    -22.88
     implement
    -22.38
    function
    -22.25
    功能
    -22.25
    POSITIVE LOGITS
     subscribers
    17.25
    技术水平
    16.88
    缀
    16.63
    [sub
    15.94
     subscriptions
    15.56
    协会
    14.69
    用户的
    14.44
    Pattern
    14.44
     Subcommittee
    14.31
     pattern
    14.25
    Activations Density 0.976%

    No Known Activations