© 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. 14342
    Prev
    Next
    INDEX
    Explanations

    latitude

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

    No Comments

    Negative Logits
    XE
    -19.50
    .CONFIG
    -18.75
    [unit
    -18.13
    rats
    -18.13
    olatile
    -18.13
    Css
    -17.88
    嚏
    -17.63
    ilio
    -17.50
    OfWork
    -17.38
     createContext
    -17.38
    POSITIVE LOGITS
     lat
    18.38
     Dek
    13.69
    lat
    13.00
    templ
    13.00
    12.88
     templ
    12.81
     Lat
    12.00
     amb
    12.00
     set
    11.94
    笠
    11.69
    Activations Density 0.026%

    No Known Activations