© 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. 14983
    Prev
    Next
    INDEX
    Explanations

    garlic

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

    No Comments

    Negative Logits
    <tag
    -20.25
    ��
    -17.50
    静态
    -16.75
    >tag
    -16.50
    成份
    -16.13
    posição
    -16.13
    Twig
    -15.94
     Static
    -15.44
     sito
    -15.38
     Sexo
    -15.31
    POSITIVE LOGITS
     bulbs
    15.69
    大蒜
    15.56
     spheres
    14.56
    zar
    14.56
    ლ
    14.31
    zek
    13.94
    蒜
    13.81
    鳞
    13.81
    ersen
    13.50
    洋葱
    13.44
    Activations Density 0.051%

    No Known Activations