© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1590
    Prev
    Next
    INDEX
    Explanations

    say "ocean" names

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

    No Comments

    Negative Logits
    India
    -39.50
     India
    -38.00
    Indian
    -37.50
     Indian
    -37.25
    印度
    -35.75
    浙江省
    -27.50
     Indians
    -27.00
    浙江
    -26.88
     indian
    -26.50
     india
    -26.25
    POSITIVE LOGITS
    .widget
    19.88
    文档
    18.75
     skeletal
    17.13
    光
    17.13
     token
    16.50
     dok
    16.38
    words
    16.13
    .tokens
    15.94
    widget
    15.63
     DOC
    15.56
    Activations Density 0.129%

    No Known Activations