© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34744
    Prev
    Next
    INDEX
    Explanations

    adults and related age groups

    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
    à¹Ģà¸Ķà¹ĩà¸ģà¹Ĩ
    -0.08
    à¹īà¸Ńà¸ĩ
    -0.07
    è¿Ļå°ıåŃIJ
    -0.07
    èĭ¦ç»ĥ
    -0.07
    éĻĪ家
    -0.07
    åĴĮä¿ĿæĬ¤
    -0.07
    .ends
    -0.07
     девоÑĩ
    -0.07
    ç»Ŀåľ°
    -0.07
    ä¸İå®īåħ¨
    -0.07
    POSITIVE LOGITS
     adult
    0.15
    æĪIJ人
    0.14
    æĪIJ年人
    0.14
     adults
    0.13
     Adult
    0.12
    Adult
    0.12
    æĪIJå¹´
    0.12
    adult
    0.12
     adulte
    0.11
     adulto
    0.11
    Activations Density 0.354%

    No Known Activations