© 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. 2597
    Prev
    Next
    INDEX
    Explanations

    say org

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

    No Comments

    Negative Logits
    校
    -18.88
    _cur
    -17.00
     ret
    -16.50
    奶奶
    -16.38
    -ret
    -15.94
     cur
    -15.88
    ���
    -15.81
    .cur
    -15.69
    .ret
    -15.56
    cur
    -15.19
    POSITIVE LOGITS
     Morgan
    46.25
    (org
    36.25
     org
    36.00
     organ
    35.25
    	org
    34.75
    morgan
    34.75
     Org
    33.00
    器官
    33.00
    机关
    32.50
    有机
    32.50
    Activations Density 0.018%

    No Known Activations