© 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. 2041
    Prev
    Next
    INDEX
    Explanations

    civil war

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

    No Comments

    Negative Logits
     america
    -22.50
     Lincoln
    -21.88
     America
    -21.00
    merican
    -20.25
    Americans
    -20.00
    American
    -19.38
    -Americ
    -19.38
     Americas
    -19.00
     americ
    -18.75
     Stmt
    -18.75
    POSITIVE LOGITS
    科学
    15.00
     science
    14.25
    ψ
    13.75
    钢
    13.69
    鲩
    13.69
    fish
    13.56
    蛋白
    13.50
    火
    13.38
    .gamma
    13.13
    istas
    13.06
    Activations Density 0.129%

    No Known Activations