© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 462
    Prev
    Next
    INDEX
    Explanations

    literary characters

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

    No Comments

    Negative Logits
     Cameroon
    -25.25
     Lebanese
    -25.25
     Lebanon
    -25.13
     Malaysia
    -24.88
     Liberia
    -24.50
     Kimber
    -23.88
     Ghana
    -23.25
     Malaysian
    -23.13
    马来西亚
    -23.00
     Tanzania
    -22.88
    POSITIVE LOGITS
     SG
    18.25
    ptom
    17.25
    (fs
    17.25
    GS
    17.13
    fs
    17.13
    /fs
    17.00
     fs
    16.75
    Resolution
    16.63
    萧
    16.38
    gs
    16.25
    Activations Density 0.119%

    No Known Activations