© 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. 846
    Prev
    Next
    INDEX
    Explanations

    say android

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

    No Comments

    Negative Logits
    连云港
    -21.75
     Aberdeen
    -21.25
    泰州
    -19.75
     Glasgow
    -19.50
     Brunswick
    -19.00
     Lyme
    -19.00
     Charlottesville
    -18.63
    老虎
    -18.38
    葡萄
    -18.25
     Missouri
    -18.00
    POSITIVE LOGITS
     Android
    63.25
    Android
    61.00
    /android
    60.25
    -android
    60.00
     android
    58.50
    android
    57.25
    (Android
    56.50
    _android
    55.25
    (android
    53.00
    .Android
    49.25
    Activations Density 0.203%

    No Known Activations