© 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. 15062
    Prev
    Next
    INDEX
    Explanations

    senior titles

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

    No Comments

    Negative Logits
    bung
    -16.75
    机械化
    -16.63
    .rows
    -16.13
    .transport
    -16.00
    lug
    -16.00
    _ROWS
    -15.56
     row
    -15.50
    风格
    -15.44
    功
    -15.13
    交通工具
    -15.13
    POSITIVE LOGITS
    projects
    17.13
     Executive
    16.38
     projects
    16.00
     executive
    15.81
     programs
    15.56
     products
    14.88
     exec
    14.88
    programs
    14.31
    Executive
    14.19
    ERV
    14.13
    Activations Density 0.067%

    No Known Activations