© 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. 1447
    Prev
    Next
    INDEX
    Explanations

    [bone] => [bone]

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

    No Comments

    Negative Logits
    璜
    -18.38
    葡萄酒
    -16.75
    hta
    -16.75
    文化传播
    -16.75
     SAFE
    -16.75
    ButtonDown
    -16.50
    奥运会
    -16.13
    石榴
    -16.13
     marketplace
    -16.00
    居室
    -16.00
    POSITIVE LOGITS
    /Linux
    18.00
     AI
    17.13
     IPs
    17.00
     IP
    16.88
    [ip
    16.63
    Echo
    15.88
    -ip
    15.75
     Linux
    15.69
    _IP
    15.56
    AI
    15.50
    Activations Density 0.041%

    No Known Activations