© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15707
    Prev
    Next
    INDEX
    Explanations

    [cerebro] => [sp]

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

    No Comments

    Negative Logits
     Roz
    -18.88
     Klopp
    -18.38
     XK
    -17.88
    bz
    -17.75
     Kou
    -17.25
    orgh
    -17.13
     Hungary
    -16.88
     kz
    -16.75
    珞
    -16.50
    分校
    -16.38
    POSITIVE LOGITS
     spinal
    17.38
    泄漏
    17.38
     Fountain
    16.50
     leaking
    16.13
    acific
    16.00
    space
    16.00
    脊
    16.00
    液体
    15.38
     leaks
    15.13
    荚
    15.06
    Activations Density 0.043%

    No Known Activations