© 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. 15684
    Prev
    Next
    INDEX
    Explanations

    geopolitical conflict

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

    No Comments

    Negative Logits
     Measurements
    -17.75
    -oper
    -17.38
     measurements
    -17.13
    WebResponse
    -16.13
     testim
    -16.00
     measurement
    -15.94
    perse
    -15.44
    FindObject
    -15.38
    遹
    -15.31
    òn
    -15.25
    POSITIVE LOGITS
    特朗普
    17.50
    强奸
    17.25
    _cart
    17.13
    媒体
    16.75
    炸弹
    16.63
    美国人
    16.13
    美军
    16.00
    MEDIA
    15.88
    投资基金
    15.81
    抗生素
    15.81
    Activations Density 0.344%

    No Known Activations