© 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. 15218
    Prev
    Next
    INDEX
    Explanations

    say ng

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

    No Comments

    Negative Logits
     Ng
    -28.50
    Ng
    -28.38
    ng
    -28.38
    agi
    -27.50
    agle
    -27.50
    ag
    -26.63
    inging
    -26.13
     ng
    -25.75
    _ng
    -25.50
     Mg
    -25.25
    POSITIVE LOGITS
    廉
    16.13
    .memo
    14.38
     Sheldon
    14.31
    heet
    14.00
    naire
    13.88
    ChildIndex
    13.63
    iani
    13.56
    юр
    13.56
     Lex
    13.56
     volta
    13.50
    Activations Density 0.162%

    No Known Activations