© 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. 883
    Prev
    Next
    INDEX
    Explanations

    say proper names

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

    No Comments

    Negative Logits
    武汉市
    -24.38
     QtCore
    -20.88
    郑州
    -20.50
    武汉
    -20.38
    湖北
    -20.13
     TK
    -20.00
    宜昌
    -19.75
    Ohio
    -19.38
     Ohio
    -19.13
    郑州市
    -19.13
    POSITIVE LOGITS
     Gott
    17.25
    rina
    16.63
     Casc
    16.13
    ');");↵
    15.13
    羲
    14.63
     Werner
    14.38
     Magnus
    14.13
     Cru
    13.81
     Crist
    13.75
     Fus
    13.75
    Activations Density 0.277%

    No Known Activations