© 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. 15334
    Prev
    Next
    INDEX
    Explanations

    [font-size:] => [font-size:]

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

    No Comments

    Negative Logits
    -driving
    -15.75
     hoog
    -15.56
    轸
    -14.75
    quam
    -14.38
     disregard
    -13.94
     cease
    -13.63
    外国语
    -13.63
    croft
    -13.56
     Glad
    -13.56
    !",↵
    -13.56
    POSITIVE LOGITS
    azen
    18.00
    绞
    15.88
    ersed
    15.88
    璠
    14.81
    еб
    14.81
    annotations
    14.69
    蓟
    14.63
    erview
    14.44
    idden
    14.44
    izen
    14.38
    Activations Density 0.014%

    No Known Activations