© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15164
    Prev
    Next
    INDEX
    Explanations

    [first name] => [surname]

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

    No Comments

    Negative Logits
    ailing
    -17.75
    PEAR
    -16.75
     spoiled
    -15.75
    (validate
    -15.75
    ahu
    -15.69
    匏
    -15.69
     Spo
    -15.13
    oyer
    -15.06
    葫芦
    -15.06
    地狱
    -14.88
    POSITIVE LOGITS
    étr
    17.50
    客流
    16.75
     lakh
    15.81
     clim
    15.31
    flow
    14.69
    吞
    14.69
    ampp
    14.63
    stag
    14.56
     Phy
    14.56
     flow
    14.50
    Activations Density 0.043%

    No Known Activations