© 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. 1863
    Prev
    Next
    INDEX
    Explanations

    [psychology] => [mental]

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

    No Comments

    Negative Logits
     psychological
    -60.50
     psychology
    -60.25
    心理
    -57.00
     Psychology
    -55.75
    心理学
    -54.50
     Psychological
    -54.00
    Psych
    -52.00
    的心理
    -51.50
     psychologists
    -50.75
     psychologically
    -49.50
    POSITIVE LOGITS
    lambda
    20.63
    LED
    16.50
     LED
    16.50
     lambda
    16.25
    兰
    15.13
    羊
    14.81
    λ
    14.56
    SHOT
    14.13
    制造
    13.94
     북한
    13.69
    Activations Density 0.182%

    No Known Activations