© 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. 1452
    Prev
    Next
    INDEX
    Explanations

    [Holy] => [Spirit]

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

    No Comments

    Negative Logits
     logic
    -21.88
    逻辑
    -20.75
    .logic
    -19.25
     graphic
    -18.88
    icity
    -18.13
    仪器
    -18.13
    logic
    -18.00
     graphics
    -18.00
    icons
    -17.63
     Graphics
    -17.50
    POSITIVE LOGITS
    Salt
    19.25
     salt
    19.13
    salt
    18.63
    _salt
    17.63
     Salt
    17.00
    Sal
    15.94
    angular
    15.88
    ϑ
    15.88
    篝
    15.69
     sal
    15.13
    Activations Density 0.234%

    No Known Activations