© 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. 14468
    Prev
    Next
    INDEX
    Explanations

    In

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

    No Comments

    Negative Logits
    ings
    -17.13
    abet
    -16.13
    inker
    -15.56
    禁忌
    -15.38
    ingle
    -15.19
    bero
    -15.00
    群
    -14.06
    ên
    -13.88
    ins
    -13.69
    ра
    -13.69
    POSITIVE LOGITS
    ServiceImpl
    16.88
     CHAPTER
    16.50
     binder
    15.69
    accumulator
    15.44
     Cree
    15.06
     architectural
    15.06
    舂
    15.06
    toolbar
    15.00
    TabIndex
    14.88
    Routing
    14.75
    Activations Density 0.142%

    No Known Activations