© 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. 60923
    Prev
    Next
    INDEX
    Explanations

    control and design

    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¿¡ä»»åĴĮ
    -0.07
    ç«ĻåĨħæIJľç´¢
    -0.07
    絡
    -0.07
    ÑĤÑı
    -0.07
     Automatically
    -0.07
     automatically
    -0.07
    _processes
    -0.06
     trust
    -0.06
    ä¿¡ä»»
    -0.06
    çĶŁæĢķ
    -0.06
    POSITIVE LOGITS
    åı¯æݧ
    0.18
    éļıå¿ĥæīĢ欲
    0.16
    æĵįæݧ
    0.15
    æݧåĪ¶
    0.15
     control
    0.14
     controlled
    0.14
    /control
    0.13
    æݧåĪ¶çļĦ
    0.13
    æݧåĪ¶æĿĥ
    0.13
    è°ĥæݧ
    0.13
    Activations Density 0.483%

    No Known Activations