© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30089
    Prev
    Next
    INDEX
    Explanations

    guardianship, infant, minor, age

    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
    å¨ĺåŃIJ
    -0.10
    okrat
    -0.09
    yaj
    -0.09
    ejas
    -0.08
    æĪIJåijĺåįķä½į
    -0.08
    åĩ°
    -0.08
    agri
    -0.08
     bret
    -0.08
    ä¸ĬçıŃæŶéĹ´
    -0.08
     Mulher
    -0.08
    POSITIVE LOGITS
    æ°ijäºĭè¡Į为èĥ½åĬĽ
    0.10
     age
    0.10
     disability
    0.09
    å¹´é¾Ħ
    0.09
    æĩµæĩĤ
    0.09
    年满
    0.09
    æĻºåĬĽ
    0.08
    æĪIJå¹´
    0.08
    æ°ijäºĭè¡Į为
    0.08
     disabilities
    0.08
    Activations Density 0.023%

    No Known Activations