© 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. 14256
    Prev
    Next
    INDEX
    Explanations

    N/A

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

    No Comments

    Negative Logits
     project
    -32.25
    项目
    -30.63
    项目的
    -30.38
     projects
    -28.88
     PROJECT
    -28.25
    project
    -27.75
     Project
    -27.75
    Project
    -27.50
    _project
    -26.25
     proj
    -26.25
    POSITIVE LOGITS
    调
    20.50
    調
    18.63
    ventus
    15.63
    技术服务
    15.44
     call
    15.44
    考生
    15.25
    unction
    15.25
    (call
    14.94
    ierge
    14.94
    interop
    14.88
    Activations Density 0.733%

    No Known Activations