© 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. 43338
    Prev
    Next
    INDEX
    Explanations

    hen dos, saphenous vein, Prader-Willi syndrome

    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
    ä¸ĢåľĪ
    -0.07
    å§IJå¼Ł
    -0.07
    Welcome
    -0.06
    æļ¨
    -0.06
    åĪĨæ°´
    -0.06
    _split
    -0.06
    agh
    -0.06
    اشت
    -0.06
    cent
    -0.06
    æŃ»ä¸į
    -0.06
    POSITIVE LOGITS
    åıįä¹ĭ
    0.11
     Conversely
    0.09
     vice
    0.08
    缸åıįçļĦ
    0.08
    unds
    0.08
    åįķæĸ¹éĿ¢
    0.08
    ä¿
    0.08
    /OR
    0.08
    /left
    0.08
    ünde
    0.08
    Activations Density 0.276%

    No Known Activations