© 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. 14138
    Prev
    Next
    INDEX
    Explanations

    say function

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

    No Comments

    Negative Logits
    amodel
    -14.38
    运气
    -13.56
     SAMPLE
    -13.00
    样本
    -13.00
    벨
    -12.94
    .Keyboard
    -12.88
    驮
    -12.88
    elda
    -12.75
     samples
    -12.75
    톤
    -12.63
    POSITIVE LOGITS
     function
    79.00
     Function
    78.00
     functions
    76.50
    Function
    73.50
     Functions
    73.00
    函数
    72.50
    function
    72.00
    功能
    68.50
    functions
    68.50
    -function
    67.00
    Activations Density 1.618%

    No Known Activations