© 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. 1802
    Prev
    Next
    INDEX
    Explanations

    [New] => [York]

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

    No Comments

    Negative Logits
    纽约
    -29.25
     NYC
    -29.00
    NY
    -29.00
     NYPD
    -27.13
     NY
    -27.13
     NYT
    -26.13
    ニュ
    -24.75
     New
    -23.00
    紐
    -22.88
     Nep
    -20.75
    POSITIVE LOGITS
    炭
    18.63
    碳
    16.38
    肩
    16.13
     burner
    15.25
     carbon
    14.75
    _bias
    13.94
    sil
    13.81
    排骨
    13.81
    carbon
    13.75
    marine
    13.69
    Activations Density 0.195%

    No Known Activations