© 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. 46322
    Prev
    Next
    INDEX
    Explanations

    metallothionein, trace elements, sterols, viruses, frameworks

    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
    ÙĪدÛĮ
    -0.07
    å¥ĭ
    -0.07
    oda
    -0.06
     <![
    -0.06
    ÃŃž
    -0.06
    æĥ³æ³ķ
    -0.06
    iani
    -0.06
    onado
    -0.06
     Gould
    -0.06
    æĺ¯ä»Ģä¹Īæł·çļĦ
    -0.06
    POSITIVE LOGITS
    åIJĦèĩª
    0.10
    åIJĦèĩªçļĦ
    0.09
    åIJĦæľīåIJĦ
    0.09
     respective
    0.09
    åIJį称
    0.09
    åIJĦæľī
    0.08
     wymien
    0.08
    ãģĿãĤĮãģŀãĤĮ
    0.08
    URRE
    0.08
     mentioned
    0.08
    Activations Density 0.153%

    No Known Activations