© 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. 55651
    Prev
    Next
    INDEX
    Explanations

    vertex, Sussex, settings, android, world, popular, ELS, python, parent, bridge

    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»İ
    -0.09
    ÑĬÑĤ
    -0.08
    ä»İåħ¶
    -0.08
    ÙĮÙij
    -0.07
    ä»İ鼶
    -0.07
    imates
    -0.07
    ä»İæĹł
    -0.07
    å¿ĥä¸ŃçļĦ
    -0.07
    åľ°ä»İ
    -0.07
    ÙĮ
    -0.07
    POSITIVE LOGITS
     standpoint
    0.17
    å®ŀéĻħåĩºåıij
    0.17
     onwards
    0.15
     perspective
    0.14
    æºIJ头ä¸Ĭ
    0.14
    è§Ĵ度åĩºåıij
    0.14
    æĥħåĨµæĿ¥çľĭ
    0.13
     outset
    0.13
    ä¸ŃæıIJåıĸ
    0.13
    è§Ĵ度çľĭ
    0.13
    Activations Density 0.791%

    No Known Activations