© 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. 1745
    Prev
    Next
    INDEX
    Explanations

    [killed] => [number]

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

    No Comments

    Negative Logits
     Murder
    -19.50
     élect
    -17.88
     manufacturing
    -17.50
     Melania
    -17.50
     kettle
    -17.00
     murder
    -16.63
    杀人
    -16.13
    用电
    -16.13
    来电
    -15.88
    杀
    -15.69
    POSITIVE LOGITS
    font
    23.13
     font
    21.88
     Courtney
    19.88
    (font
    19.75
    _font
    19.38
    _FONT
    18.13
    Font
    18.00
     Font
    17.75
    法官
    17.50
    bart
    17.25
    Activations Density 0.106%

    No Known Activations