© 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. 15345
    Prev
    Next
    INDEX
    Explanations

    elixir

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

    No Comments

    Negative Logits
    中超
    -17.38
    环
    -17.00
    闭环
    -15.81
     Airbnb
    -15.50
    _Trans
    -15.31
    芮
    -15.13
    UPI
    -15.00
    Circular
    -14.69
    NaN
    -14.63
     Travis
    -14.38
    POSITIVE LOGITS
    lixir
    17.63
    药师
    17.25
    膏
    16.75
    医科
    16.50
     Pistol
    16.00
    .nlm
    15.56
    yll
    15.50
    _dll
    15.31
    rams
    15.31
     drip
    14.94
    Activations Density 0.172%

    No Known Activations