© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3100
    Prev
    Next
    INDEX
    Explanations

    say digits

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     result
    -20.00
    房屋
    -19.63
    (result
    -18.25
    结果
    -17.75
     property
    -15.63
    组合
    -15.50
    性质
    -15.44
    一组
    -15.44
    _result
    -15.38
    =result
    -15.25
    POSITIVE LOGITS
    例
    23.75
     class
    18.75
    element
    18.63
    全镇
    18.63
    ELEMENT
    18.38
    Example
    18.25
    class
    18.00
    Element
    17.75
     Example
    17.75
    	class
    17.63
    Activations Density 0.361%

    No Known Activations