© 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. 15340
    Prev
    Next
    INDEX
    Explanations

    土木之变

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

    No Comments

    Negative Logits
    汽车行业
    -17.38
    phis
    -17.13
    angler
    -16.75
    汽车产业
    -16.25
    化肥
    -15.88
    加盟店
    -15.75
    ClientId
    -15.69
     gluten
    -15.63
     chemistry
    -15.56
    sell
    -15.56
    POSITIVE LOGITS
    eday
    14.94
     Meghan
    14.88
     Woj
    14.19
    卫
    13.88
    Desc
    13.75
    导航
    13.56
     Secure
    13.50
    彩
    13.38
     Encryption
    13.38
    (desc
    13.38
    Activations Density 0.135%

    No Known Activations