© 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. 14451
    Prev
    Next
    INDEX
    Explanations

    say digit

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

    No Comments

    Negative Logits
    uelles
    -22.00
    alem
    -21.00
    inaire
    -19.13
    aceous
    -18.63
    ses
    -18.50
    oons
    -18.50
    inals
    -17.88
    �
    -17.88
     Salon
    -17.75
    icans
    -17.63
    POSITIVE LOGITS
    ped
    12.94
    дж
    12.94
    msp
    12.56
    热
    12.56
    .optimizer
    12.38
    .viewDidLoad
    12.38
    桢
    12.38
    hea
    12.31
     Adler
    12.19
    热度
    11.88
    Activations Density 0.021%

    No Known Activations