© 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. 1926
    Prev
    Next
    INDEX
    Explanations

    æĻºèĥ½ and åĨħåŃĺ

    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
    sWith
    -0.11
    ا
    -0.10
    аем
    -0.09
    a
    -0.09
    ÏĤ
    -0.08
    ами
    -0.08
    enticate
    -0.08
    ing
    -0.08
    åĬĽè¡Į
    -0.07
    ifications
    -0.07
    POSITIVE LOGITS
    à§įন
    0.09
    åįģ足çļĦ
    0.09
    æĪijä¸įè¦ģ
    0.08
    oguÄĩ
    0.08
    /disable
    0.08
    ÙĬجة
    0.08
    arendra
    0.08
    peror
    0.08
    hver
    0.08
    ħ
    0.08
    Activations Density 0.001%

    No Known Activations