© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14643
    Prev
    Next
    INDEX
    Explanations

    [the] => [the]

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

    No Comments

    Negative Logits
    ellipsis
    -21.13
    iele
    -21.00
    Apollo
    -20.63
    apollo
    -20.25
    蝶
    -20.13
    古城
    -20.00
     Alexis
    -19.75
    虹桥
    -19.75
    希腊
    -19.63
     Athens
    -19.50
    POSITIVE LOGITS
    bins
    15.44
     Bark
    14.19
    bert
    13.88
    ub
    13.75
     Shark
    12.94
    cv
    12.88
    伐
    12.88
    毓
    12.63
    azz
    12.44
     vig
    12.38
    Activations Density 0.095%

    No Known Activations