© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1326
    Prev
    Next
    INDEX
    Explanations

    elements

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

    No Comments

    Negative Logits
    _Element
    -23.13
    党员
    -23.00
    ELEMENT
    -22.50
    元素
    -21.88
    widget
    -21.25
     Element
    -21.13
     widget
    -20.88
     element
    -20.75
     Widgets
    -20.50
    (widget
    -20.25
    POSITIVE LOGITS
     Python
    18.00
     python
    17.88
    Python
    17.50
    酒
    17.25
    python
    16.50
    文学
    16.50
    PYTHON
    15.88
    酒业
    15.69
    Phys
    15.50
    诗
    15.38
    Activations Density 0.223%

    No Known Activations