© 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. 14803
    Prev
    Next
    INDEX
    Explanations

    English kings

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

    No Comments

    Negative Logits
    ober
    -20.50
    UNS
    -16.75
     Umb
    -16.13
    obl
    -15.69
    tras
    -15.63
    iren
    -15.50
    .Protocol
    -15.13
     DK
    -15.06
     Domain
    -14.88
    osen
    -14.81
    POSITIVE LOGITS
    assi
    14.25
    ertest
    13.63
    .testing
    13.38
    Survey
    13.31
     projectId
    13.25
     survey
    13.25
    Assignment
    13.06
    逃跑
    12.69
     ASSIGN
    12.50
    输卵管
    12.50
    Activations Density 0.050%

    No Known Activations