© 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. 3161
    Prev
    Next
    INDEX
    Explanations

    say numbers

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    性质
    -21.88
    班
    -21.13
     class
    -21.00
    班级
    -20.25
    subclass
    -18.88
    (class
    -18.88
     network
    -18.63
     chapter
    -18.38
    	class
    -18.25
    ,class
    -18.00
    POSITIVE LOGITS
    .addElement
    18.13
     Manager
    17.75
    coli
    17.75
     Equation
    17.75
     manager
    17.50
     Member
    17.50
    manager
    16.75
    _element
    16.63
    <Element
    16.63
     Approach
    16.38
    Activations Density 0.207%

    No Known Activations