© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 28880
    Prev
    Next
    INDEX
    Explanations

    son's or daughter's parents' professions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è±
    -0.07
    å¸Īå¼Ł
    -0.07
    friend
    -0.07
    assen
    -0.07
    以为èĩªå·±
    -0.07
     puls
    -0.06
    gir
    -0.06
     Marino
    -0.06
    izion
    -0.06
    ulli
    -0.06
    POSITIVE LOGITS
    对åŃ©åŃIJçļĦ
    0.12
    为åŃ©åŃIJ
    0.10
    åľ¨åŃ©åŃIJ
    0.10
    ç»ĻåŃ©åŃIJ
    0.10
     grandparents
    0.09
     parents
    0.09
    è¨Ģä¼ł
    0.09
     Parent
    0.09
     ÑĢодиÑĤелÑĮ
    0.09
    ä¸İåŃ©åŃIJ
    0.09
    Activations Density 0.333%

    No Known Activations