© 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. 1665
    Prev
    Next
    INDEX
    Explanations

    chemical elements

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

    No Comments

    Negative Logits
     Magnus
    -17.25
    Û
    -16.25
     Scandinavian
    -15.81
     Kling
    -15.69
    合法
    -15.50
     Alps
    -15.44
    游戏玩家
    -14.81
    Spi
    -14.69
    嗽
    -14.44
    挪威
    -14.38
    POSITIVE LOGITS
    钙
    20.88
     BED
    20.25
     calcium
    19.63
     Bed
    19.38
    床
    19.38
    河南
    19.13
    earth
    18.75
     Calcium
    18.50
    BED
    18.38
     sleep
    18.25
    Activations Density 0.395%

    No Known Activations