© 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. 15278
    Prev
    Next
    INDEX
    Explanations

    the

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

    No Comments

    Negative Logits
    ,’”
    -12.56
    ”;
    -11.69
    读后
    -11.13
    ’:
    -11.00
    ”),
    -10.63
    都能够
    -10.63
    suspend
    -10.44
    ”).
    -10.13
    挂着
    -10.13
    ’.
    -10.00
    POSITIVE LOGITS
    Query
    18.75
     
    17.25
    ống
    17.13
     Algorithm
    16.88
    algo
    16.75
    ��索
    16.63
    鸢
    16.63
    dbName
    16.25
     Query
    16.13
    柚
    16.13
    Activations Density 0.201%

    No Known Activations