© 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. 15412
    Prev
    Next
    INDEX
    Explanations

    say "royalty"

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

    No Comments

    Negative Logits
    mez
    -19.25
    商务部
    -18.00
    zier
    -17.63
    zet
    -17.50
    商用
    -17.25
    [offset
    -17.00
    .mixer
    -16.50
    verbatim
    -16.38
     recycle
    -16.25
    运营管理
    -15.88
    POSITIVE LOGITS
    皇冠
    16.50
     reigning
    15.31
     ang
    14.13
    公主
    13.88
    jure
    13.69
     angst
    13.56
     Sussex
    13.44
    英
    13.38
     männ
    13.38
     Edwards
    13.31
    Activations Density 0.182%

    No Known Activations