© 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. 1051
    Prev
    Next
    INDEX
    Explanations

    [washing] => [washers]

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

    No Comments

    Negative Logits
     Washing
    -27.13
     washing
    -26.88
     Wash
    -25.38
    calc
    -24.63
     wash
    -24.38
     Calcul
    -24.13
     Washer
    -24.00
    wash
    -23.50
    calcul
    -23.50
     Calc
    -22.13
    POSITIVE LOGITS
     med
    17.88
    创新
    17.63
    спор
    17.25
    _med
    17.13
    sym
    17.13
    诗句
    16.88
    創新
    16.63
    Med
    16.63
    岭南
    16.38
     energy
    16.25
    Activations Density 0.117%

    No Known Activations