© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15190
    Prev
    Next
    INDEX
    Explanations

    parenthetical legal citations

    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
    çµ®
    -0.08
    wür
    -0.07
    édia
    -0.07
    ç«ŀäºīæĢ§
    -0.07
    enal
    -0.07
    ê·Ģ
    -0.07
    漪
    -0.07
    _TRY
    -0.07
    िर
    -0.07
    æĽ´éĩįè¦ģçļĦ
    -0.07
    POSITIVE LOGITS
    amol
    0.07
    emed
    0.07
    .Merge
    0.06
    å¦Ĥ鼨
    0.06
    ä¸ŃæĪIJéķ¿
    0.06
     bes
    0.06
    angler
    0.06
    æĭ¼
    0.06
     (;;
    0.06
    AP
    0.06
    Activations Density 0.002%

    No Known Activations