© 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. 1266
    Prev
    Next
    INDEX
    Explanations

    [rivers] => [lakes]

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

    No Comments

    Negative Logits
     river
    -44.50
    River
    -44.00
     rivers
    -43.00
     River
    -43.00
     Rivers
    -38.50
    河流
    -38.50
    河
    -36.50
    river
    -35.25
    河边
    -33.50
    河水
    -29.25
    POSITIVE LOGITS
    Te
    15.75
    Fault
    15.56
    fault
    15.50
    ijkl
    14.94
     Authentic
    14.38
    _PS
    14.19
     الصحة
    14.13
     diagnostic
    14.06
    .palette
    14.00
    骨
    14.00
    Activations Density 0.090%

    No Known Activations