© 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. 15330
    Prev
    Next
    INDEX
    Explanations

    say digits

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

    No Comments

    Negative Logits
    immer
    -18.50
    /cms
    -16.75
    immers
    -16.75
    (balance
    -16.63
    皓
    -16.63
    IGO
    -16.63
    codes
    -16.63
    pie
    -16.50
    مين
    -16.00
    该游戏
    -15.94
    POSITIVE LOGITS
     marks
    14.63
    Acts
    13.63
    nd
    13.63
    Answers
    12.94
    MARK
    12.88
     len
    12.75
     co
    12.63
     cf
    12.56
     Churchill
    12.44
     mul
    12.31
    Activations Density 0.034%

    No Known Activations