© 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. 14819
    Prev
    Next
    INDEX
    Explanations

    say "boundary" words

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

    No Comments

    Negative Logits
    _la
    -16.13
    瑜
    -15.94
    ROT
    -15.94
    ulas
    -15.88
    leet
    -15.75
    ampoo
    -15.31
    首发
    -15.31
    (OpCodes
    -15.25
    爱吃
    -14.88
     Loft
    -14.75
    POSITIVE LOGITS
    边界
    56.00
     boundary
    55.25
     Boundary
    49.00
     boundaries
    46.75
     border
    46.75
    boundary
    46.00
    界
    46.00
    _boundary
    44.75
    Boundary
    44.50
     borders
    43.75
    Activations Density 0.206%

    No Known Activations