© 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. 14921
    Prev
    Next
    INDEX
    Explanations

    say 8

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

    No Comments

    Negative Logits
    MIT
    -17.63
    osph
    -17.00
    oj
    -16.63
    afka
    -16.50
    yc
    -16.38
    kah
    -16.13
    爆发
    -15.75
    omes
    -15.69
    omed
    -15.56
    otas
    -15.44
    POSITIVE LOGITS
    inery
    16.13
    ENO
    16.00
    玲
    15.13
    imson
    15.06
    wheel
    14.81
     Chevron
    14.69
    inati
    14.50
    erville
    14.44
    秤
    14.31
    恂
    14.31
    Activations Density 0.033%

    No Known Activations