© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1388
    Prev
    Next
    INDEX
    Explanations

    [电缆] => [电缆]

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

    No Comments

    Negative Logits
     Claude
    -16.75
     paul
    -16.63
     diagonal
    -16.00
    Paul
    -15.94
    Script
    -15.88
    界面
    -15.81
    保罗
    -15.75
     Brett
    -15.69
     Bauer
    -15.63
    CI
    -15.50
    POSITIVE LOGITS
     business
    17.75
    business
    16.88
    照
    16.75
    /photos
    16.75
     Foto
    16.75
     pok
    16.50
    ��
    16.38
    istan
    16.38
    业务
    15.94
    цев
    15.50
    Activations Density 0.399%

    No Known Activations