© 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. 14132
    Prev
    Next
    INDEX
    Explanations

    say species

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

    No Comments

    Negative Logits
    组件
    -23.38
    实验
    -20.13
    	component
    -19.38
    测试
    -18.88
    输入
    -18.75
     demo
    -18.63
    demo
    -18.25
    改革
    -18.00
    -demo
    -17.63
    模型
    -17.63
    POSITIVE LOGITS
     species
    17.25
    蓝色
    15.88
    ascus
    15.63
    Species
    15.50
    物种
    15.25
     scientifically
    15.19
    icolor
    15.19
     Species
    15.13
     blue
    15.06
    species
    14.94
    Activations Density 0.770%

    No Known Activations