© 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. 14212
    Prev
    Next
    INDEX
    Explanations

    say material

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

    No Comments

    Negative Logits
     function
    -23.00
    Function
    -22.75
    	function
    -21.75
     functions
    -21.38
     Function
    -21.38
    _function
    -21.25
    function
    -20.63
    .Function
    -20.63
    函数
    -20.50
    -functions
    -20.00
    POSITIVE LOGITS
    /material
    17.00
    Materials
    16.88
     materials
    16.75
    材料
    16.63
     Materials
    16.50
     material
    16.50
    paired
    15.81
     MATERIAL
    15.69
    Material
    15.63
    _COMBO
    15.63
    Activations Density 1.069%

    No Known Activations