© 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. 15181
    Prev
    Next
    INDEX
    Explanations

    full term => abbreviation

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

    No Comments

    Negative Logits
    ad
    -33.50
    ads
    -28.75
    ад
    -28.63
     ad
    -28.13
    adr
    -26.38
    aden
    -25.75
     Ad
    -25.13
    sad
    -25.13
    od
    -24.50
    (ad
    -23.88
    POSITIVE LOGITS
    hol
    16.00
     bureau
    14.19
    询
    14.00
    簿
    13.44
    erville
    13.38
    stro
    13.31
    ylon
    13.06
    Ầ
    13.00
    茄子
    12.81
    浏览
    12.69
    Activations Density 0.204%

    No Known Activations