© 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. 15764
    Prev
    Next
    INDEX
    Explanations

    new

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

    No Comments

    Negative Logits
    handleRequest
    -16.38
     shovel
    -16.13
    被执行
    -15.69
     autoload
    -15.44
    ackbar
    -14.94
    分离
    -14.44
     sulfate
    -14.13
    .enqueue
    -14.13
    _sensitive
    -13.81
    Rejected
    -13.81
    POSITIVE LOGITS
    一轮
    18.75
    釋
    17.50
    无忧
    16.75
    방
    16.63
    额头
    16.00
    ��
    15.94
     cycle
    15.94
    cycle
    15.88
     Cycle
    15.56
    ⼊
    15.56
    Activations Density 0.163%

    No Known Activations