© 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. 14744
    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
     pard
    -17.88
    getBody
    -17.88
    TagName
    -17.75
    PID
    -17.50
    .getBody
    -17.13
    tabpanel
    -16.38
    ;base
    -16.38
    inned
    -16.25
    基础知识
    -16.13
     Body
    -15.88
    POSITIVE LOGITS
    rá
    14.88
     indie
    13.75
     Icons
    13.69
    Convention
    13.56
    Independ
    12.63
    河西
    12.56
     Indie
    12.56
     Gad
    12.44
     independent
    12.25
     Abrams
    12.25
    Activations Density 0.003%

    No Known Activations