© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2448
    Prev
    Next
    INDEX
    Explanations

    say development

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

    No Comments

    Negative Logits
    模
    -17.25
    买卖
    -16.00
     module
    -15.88
    模块
    -15.69
    ��
    -15.63
    /module
    -15.63
    信息系统
    -15.63
    ocode
    -15.56
    注
    -15.13
    modulo
    -15.00
    POSITIVE LOGITS
     Development
    19.75
    Development
    19.00
     development
    18.13
     formation
    17.63
    development
    17.38
    -development
    16.63
    formation
    15.00
    田
    14.88
     Cell
    14.88
    Cell
    14.75
    Activations Density 0.008%

    No Known Activations