© 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. 992
    Prev
    Next
    INDEX
    Explanations

    say apple

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

    No Comments

    Negative Logits
    肇庆
    -24.88
    儋
    -24.50
     Nigerian
    -23.38
     Niger
    -23.25
     Venezuel
    -23.13
    茂名
    -22.75
     Nd
    -22.63
     Venezuelan
    -22.63
    漓
    -22.50
    坭
    -22.13
    POSITIVE LOGITS
    苹果
    73.50
     apple
    69.50
     Apple
    66.00
    Apple
    63.00
    apple
    61.75
     APPLE
    60.00
     apples
    57.50
    .apple
    56.50
    /apple
    56.25
    APPLE
    51.00
    Activations Density 0.090%

    No Known Activations