© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1173
    Prev
    Next
    INDEX
    Explanations

    any => 工程

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

    No Comments

    Negative Logits
    particle
    -18.88
     article
    -18.25
    GW
    -17.13
    _article
    -16.50
     Oral
    -16.13
    ula
    -16.13
     oral
    -15.75
    粒子
    -15.69
    工程
    -15.38
    article
    -15.25
    POSITIVE LOGITS
    �
    17.75
     Nav
    16.50
    ambda
    16.50
    迪
    16.13
     nav
    15.81
    的设计
    15.75
    Nav
    15.63
    𝑁
    15.63
    .Design
    15.56
    设计
    15.31
    Activations Density 0.034%

    No Known Activations