© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1537
    Prev
    Next
    INDEX
    Explanations

    [CD] => [CD4]

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

    No Comments

    Negative Logits
     CD
    -46.75
    CD
    -46.00
    _CD
    -40.00
    _cd
    -39.00
     CDs
    -38.50
     cd
    -37.50
    cd
    -35.00
    	cd
    -33.50
    (cd
    -30.38
    .cd
    -29.50
    POSITIVE LOGITS
     ngôn
    20.75
    语言
    18.25
     LANGUAGE
    17.63
    語言
    17.63
     langue
    17.25
     Rockets
    17.13
    GINE
    16.88
    рин
    16.63
    普京
    16.50
    kim
    16.13
    Activations Density 0.073%

    No Known Activations