© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 3351
    Prev
    Next
    INDEX
    Explanations

    say function

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    (func
    -22.88
    <Func
    -22.88
    (Func
    -22.63
     board
    -21.13
    板
    -19.38
    社区
    -17.75
    ListModel
    -17.75
     models
    -17.63
    searchModel
    -17.63
     Board
    -17.50
    POSITIVE LOGITS
    function
    41.00
     function
    41.00
    函数
    32.50
    Function
    32.50
     Function
    31.13
    	function
    30.63
    _function
    30.25
    -function
    27.13
    .function
    27.13
    _FUNCTION
    21.63
    Activations Density 0.058%

    No Known Activations