© 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. 61523
    Prev
    Next
    INDEX
    Explanations

    ratio, excess, weight

    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
    åĴĮ游æĪı
    -0.07
    è§ģå¾Ĺ
    -0.07
     weaker
    -0.07
    ấm
    -0.07
    oders
    -0.07
    çŀ¬éĸĵ
    -0.07
     countless
    -0.07
     sublic
    -0.06
    象å¾ģçĿĢ
    -0.06
    æ¦Ĥ
    -0.06
    POSITIVE LOGITS
    AVE
    0.08
    amna
    0.07
    amn
    0.07
    ç²¾ç¥ŀçĬ¶æĢģ
    0.07
     sparing
    0.07
     expected
    0.07
     automatico
    0.07
    å¼Ĥ常
    0.07
    empre
    0.07
    bland
    0.07
    Activations Density 0.003%

    No Known Activations