© 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. 14640
    Prev
    Next
    INDEX
    Explanations

    say 1

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

    No Comments

    Negative Logits
    warts
    -19.38
    VRT
    -19.25
     CPL
    -19.00
    ắt
    -18.50
     curses
    -18.50
     CRT
    -18.38
    aments
    -18.25
    CRT
    -18.13
     wrists
    -17.50
    ament
    -17.38
    POSITIVE LOGITS
     Accord
    17.13
     ske
    15.81
     Turnbull
    14.94
     Conv
    14.94
     Rockefeller
    14.81
    Conv
    14.69
     Sawyer
    14.63
    格局
    14.50
    ooks
    14.50
     sac
    14.50
    Activations Density 0.072%

    No Known Activations