© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1553
    Prev
    Next
    INDEX
    Explanations

    [sw] => [direction]

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

    No Comments

    Negative Logits
    游泳
    -27.38
     switches
    -27.00
     Switch
    -25.00
    switch
    -25.00
     switch
    -24.88
    -switch
    -24.63
    SW
    -24.63
    开关
    -24.38
    Switch
    -23.63
     swim
    -23.38
    POSITIVE LOGITS
     code
    17.00
     Fuß
    15.75
    代码
    15.06
     Kod
    15.00
    文献
    14.94
    纸质
    14.88
     bacterial
    14.81
    岙
    14.81
     камер
    14.56
     camera
    14.50
    Activations Density 0.074%

    No Known Activations