© 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. 1442
    Prev
    Next
    INDEX
    Explanations

    do not say wind

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

    No Comments

    Negative Logits
     wind
    -62.25
    风
    -60.25
    Wind
    -54.25
     Wind
    -52.75
     winds
    -52.00
    風
    -51.75
    wind
    -48.75
    风吹
    -46.25
    _wind
    -45.75
     Winds
    -43.00
    POSITIVE LOGITS
    蛋白
    16.13
    裁定
    15.19
     NASA
    14.50
    Pixels
    14.50
    PIX
    14.25
     Bible
    14.13
     DNA
    13.94
    chs
    13.88
     Pok
    13.69
    蛋白质
    13.63
    Activations Density 0.179%

    No Known Activations