© 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. 15257
    Prev
    Next
    INDEX
    Explanations

    weapons

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

    No Comments

    Negative Logits
    行为
    -19.63
    月饼
    -19.38
    绿豆
    -17.63
    TRACE
    -16.88
    宝石
    -16.50
     publishes
    -16.00
    /pub
    -15.88
    npos
    -15.81
    Behavior
    -15.81
     createAction
    -15.75
    POSITIVE LOGITS
    质量和
    19.00
    的质量
    17.63
    个项目
    15.94
    骑兵
    14.81
    swagen
    14.81
    投
    14.75
    vik
    14.56
    質量
    14.56
     carro
    14.50
    combo
    14.50
    Activations Density 0.120%

    No Known Activations