© 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. 958
    Prev
    Next
    INDEX
    Explanations

    say mac

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

    No Comments

    Negative Logits
    锑
    -21.63
    贵州
    -21.13
    株洲
    -21.00
    安徽
    -20.38
    珺
    -20.00
     Kentucky
    -19.50
    湖北
    -19.25
    贵州省
    -19.25
     Slovakia
    -18.50
    广西
    -18.50
    POSITIVE LOGITS
    麦克
    16.75
     Mac
    15.75
     MAC
    15.69
    麦
    15.69
    hic
    15.63
    MAC
    15.50
     PAC
    15.38
    (mac
    15.31
     mac
    15.25
    mac
    15.06
    Activations Density 0.057%

    No Known Activations