© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15540
    Prev
    Next
    INDEX
    Explanations

    place names

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

    No Comments

    Negative Logits
    蜂蜜
    -23.63
    钻石
    -23.25
    蜜
    -21.88
     Gem
    -20.38
     PIXEL
    -19.88
     Grain
    -19.88
     grain
    -19.75
     Pear
    -19.75
     gem
    -19.75
    _gem
    -19.50
    POSITIVE LOGITS
    顾问
    22.25
     Advisor
    20.13
     convent
    18.75
    _Ad
    18.38
     Outlook
    17.88
    -Con
    17.88
     Greenville
    17.50
     Prescott
    17.25
    adx
    17.25
    _CON
    17.25
    Activations Density 2.610%

    No Known Activations