© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15100
    Prev
    Next
    INDEX
    Explanations

    say industry terms

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

    No Comments

    Negative Logits
    phis
    -18.13
     Newfoundland
    -17.25
    ouro
    -16.88
     curses
    -16.88
     -:
    -16.50
    @\
    -16.50
    '',
    -16.38
     favourable
    -16.25
    rium
    -15.94
    ue
    -15.88
    POSITIVE LOGITS
    矩阵
    15.44
    教育
    14.00
    企业和
    13.56
    对应的
    13.25
    商机
    13.06
    通道
    12.88
    输
    12.81
    产业链
    12.63
    默认
    12.56
    东
    12.56
    Activations Density 0.737%

    No Known Activations