© 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. 16594
    Prev
    Next
    INDEX
    Explanations

    west, health, reproductive, finances, age, sell

    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
    åĴĮçī¹çĤ¹
    -0.07
    egos
    -0.07
    åĴĮåĬŁèĥ½
    -0.06
    ä¸İå®ŀè·µ
    -0.06
    åĴĮæĸ¹æ³ķ
    -0.06
    æľĹ
    -0.06
    ä¸İæĸ¹æ³ķ
    -0.06
    à¸ĭà¹īำ
    -0.06
    åı¯èĥ½çļĦ
    -0.06
     spur
    -0.06
    POSITIVE LOGITS
    -related
    0.11
    _related
    0.09
    æľīåħ³çļĦ
    0.09
    缸åħ³çļĦ
    0.09
    related
    0.09
    åħ¨èĪ¬
    0.09
    缸åħ³
    0.08
    sdale
    0.08
    缸åħ³ä¸ĵä¸ļ
    0.08
    olgen
    0.08
    Activations Density 1.045%

    No Known Activations