© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15477
    Prev
    Next
    INDEX
    Explanations

    不是

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

    No Comments

    Negative Logits
    Delayed
    -14.56
     Cros
    -14.38
     Rounds
    -14.19
    xDA
    -14.13
     decor
    -14.00
     Psycho
    -13.81
     stability
    -13.75
     rounds
    -13.50
     addUser
    -13.50
     link
    -13.31
    POSITIVE LOGITS
    oland
    17.00
    _SURFACE
    16.13
    边界
    15.75
    伽
    15.38
     TOM
    15.06
    技术
    15.00
    科技
    15.00
    复制
    14.88
    gan
    14.81
    gos
    14.81
    Activations Density 0.276%

    No Known Activations