© 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. 13919
    Prev
    Next
    INDEX
    Explanations

    say formulas

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

    No Comments

    Negative Logits
    属性
    -29.50
    特征
    -29.00
    特性
    -28.75
    features
    -28.75
     features
    -27.50
     Attributes
    -26.63
    feature
    -26.00
     attributes
    -25.75
     feature
    -25.63
     attribute
    -25.63
    POSITIVE LOGITS
    生产
    18.00
     formulas
    17.63
    .Term
    17.50
    公式
    17.25
     formula
    16.88
     derivation
    16.38
     term
    16.38
    支付
    15.63
    .term
    15.56
     expressions
    15.44
    Activations Density 0.683%

    No Known Activations