© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2094
    Prev
    Next
    INDEX
    Explanations

    say ser

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

    No Comments

    Negative Logits
    éis
    -15.63
    út
    -15.19
     marginal
    -14.88
    etable
    -14.31
    dí
    -13.88
    ✑
    -13.81
    边际
    -13.69
    祉
    -13.50
     Lim
    -13.44
     Soda
    -13.38
    POSITIVE LOGITS
     ser
    92.50
     Ser
    89.50
    Ser
    85.50
    ser
    80.50
    -ser
    78.50
    (serial
    78.00
    _ser
    76.00
     serial
    75.00
     Serial
    73.50
    .ser
    72.50
    Activations Density 0.324%

    No Known Activations