© 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. 22800
    Prev
    Next
    INDEX
    Explanations

    domestic, female, local, human, world, rat, global

    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
    çļĦèĥĮåIJİ
    -0.08
    ä¸ĸä¸Ĭ
    -0.07
    ä¸Ńåįİ人æ°ijåħ±åĴĮåĽ½
    -0.07
    åħ¨çIJĥæľĢ大çļĦ
    -0.07
    ä¸ŃåĽ½äººæ°ijéĵ¶è¡Į
    -0.07
    ä¸Ńä¹ĭ
    -0.07
    é«ĺçŃīä¸ĵç§ijåŃ¦æł¡
    -0.07
    çļĦéĩijé¢Ŀ
    -0.07
    ä¸ĸçķĮä¸ĬæľĢ
    -0.07
     Auton
    -0.07
    POSITIVE LOGITS
    ä¹ĥèĩ³
    0.10
    éĿŀ
    0.08
    æīĢ说
    0.07
    å®ŀéĻħåĩºåıij
    0.07
    åĴĮæĹ¥æľ¬
    0.07
    æĦıä¹īä¸ĬçļĦ
    0.07
    æĦıä¹īä¸Ĭ
    0.07
    çīĪçļĦ
    0.07
    ristol
    0.07
    OGO
    0.07
    Activations Density 0.042%

    No Known Activations