© 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. 972
    Prev
    Next
    INDEX
    Explanations

    Hebrew characters

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

    No Comments

    Negative Logits
    巴基斯坦
    -25.13
    宜昌
    -23.75
    湘西
    -23.50
     Egypt
    -23.38
     Hungarian
    -22.88
     Pakistani
    -22.88
    重庆市
    -22.88
    广西
    -22.88
     Egyptian
    -22.75
    重庆
    -22.63
    POSITIVE LOGITS
     WV
    20.00
    瓷
    18.00
     tf
    17.88
     shl
    17.75
     Lv
    17.38
    .tf
    17.38
    _tf
    17.25
    (tf
    17.13
    tf
    17.00
     hwnd
    17.00
    Activations Density 0.016%

    No Known Activations

    This feature has no known activations.