© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15559
    Prev
    Next
    INDEX
    Explanations

    Legg-Perthes

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

    No Comments

    Negative Logits
     colle
    -20.63
    (cos
    -20.00
    cos
    -19.88
    col
    -19.50
    *cos
    -19.38
     cos
    -19.38
    收集
    -19.00
    .Cos
    -18.50
     collect
    -18.25
     col
    -18.13
    POSITIVE LOGITS
     Erl
    17.25
     Carlo
    17.00
    爨
    16.75
    artial
    15.94
     Carl
    15.94
     peru
    15.88
     Petr
    15.75
    碳
    15.69
    คาร
    15.56
    oreal
    15.25
    Activations Density 1.491%

    No Known Activations