© 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. 1243
    Prev
    Next
    INDEX
    Explanations

    [Newton] => [Newton]

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

    No Comments

    Negative Logits
    Newton
    -34.75
     Newton
    -30.13
    牛
    -26.25
    牛肉
    -23.38
    Physics
    -21.50
     scientific
    -20.13
     nitrogen
    -20.00
    氮
    -20.00
    scientific
    -19.75
     fotoğraf
    -19.13
    POSITIVE LOGITS
    游戏
    15.31
    .xhtml
    15.19
    校
    14.88
    /portfolio
    14.19
    设计
    14.13
    bie
    13.94
    �
    13.81
    文化
    13.56
    /design
    13.25
     design
    13.19
    Activations Density 0.057%

    No Known Activations