© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44157
    Prev
    Next
    INDEX
    Explanations

    technicalmeasurements

    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
    zan
    -0.07
    æī
    -0.07
    obl
    -0.06
    progressbar
    -0.06
    zh
    -0.06
     genug
    -0.06
    sembl
    -0.06
    anser
    -0.06
    het
    -0.06
    èĴĻ
    -0.06
    POSITIVE LOGITS
    ä¼ĺåĵģ
    0.07
    ços
    0.07
    鹦
    0.07
     porad
    0.07
    æŁIJåĢĭ
    0.07
    æĸ¹éĿ¢çļĦéĹ®é¢ĺ
    0.06
    èĩªå¤§
    0.06
    ×ķק
    0.06
    cide
    0.06
    éĹ®é¢ĺä¸Ĭ
    0.06
    Activations Density 0.064%

    No Known Activations