© 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. 1458
    Prev
    Next
    INDEX
    Explanations

    say psych

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

    No Comments

    Negative Logits
     ELECT
    -16.88
     Elect
    -16.75
     manufacture
    -16.13
    电气
    -15.88
    电动汽车
    -15.69
    卡拉
    -15.63
     Matcher
    -15.44
     elé
    -14.94
    电工
    -14.88
    智能制造
    -14.81
    POSITIVE LOGITS
    (ps
    17.25
    _PS
    15.19
     Psych
    15.13
     climate
    15.00
    Psych
    14.94
     psychological
    14.88
    _ps
    14.81
    iggers
    14.81
     psych
    14.69
     ps
    14.38
    Activations Density 0.006%

    No Known Activations