© 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. 1011
    Prev
    Next
    INDEX
    Explanations

    say fantasy

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

    No Comments

    Negative Logits
    浦东
    -23.75
    家电
    -22.00
     Motorola
    -21.88
    塑胶
    -21.38
    汽油
    -20.50
    墨西哥
    -20.38
    动力电池
    -20.13
     Panasonic
    -19.63
     Chrysler
    -19.38
     Hoover
    -19.38
    POSITIVE LOGITS
    inja
    17.38
    奴
    16.88
     kingdom
    16.75
     king
    16.75
    公主
    16.50
     undead
    16.25
    神话
    16.00
     enchanted
    15.94
     snake
    15.81
     beast
    15.75
    Activations Density 0.285%

    No Known Activations