© 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. 2560
    Prev
    Next
    INDEX
    Explanations

    lighthouse

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

    No Comments

    Negative Logits
    商品
    -21.00
     商品
    -19.63
    病毒
    -19.25
     shopper
    -18.75
    massage
    -18.00
    DVD
    -17.75
    bout
    -17.50
     quà
    -17.25
    电子产品
    -17.25
     resale
    -17.25
    POSITIVE LOGITS
    烟囱
    15.69
     gir
    15.63
    iron
    14.63
     pier
    14.25
    yard
    13.94
     Boiler
    13.88
     tower
    13.81
     excavation
    13.75
     Sul
    13.63
    工
    13.56
    Activations Density 0.048%

    No Known Activations