© 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. 34297
    Prev
    Next
    INDEX
    Explanations

    non-word / punctuation separators

    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
    III
    -0.08
    oszt
    -0.07
    ä¸Ģ家ä¸īåı£
    -0.07
     Third
    -0.07
    åij¨ä¸ī
    -0.07
     third
    -0.07
    umas
    -0.07
    ä¸Ń年人
    -0.07
    _PARSER
    -0.06
    ä¸ī份
    -0.06
    POSITIVE LOGITS
    wap
    0.07
    tsy
    0.07
    æĴŀ
    0.06
     nata
    0.06
    ÙĤÙĬ
    0.06
    raries
    0.06
    кÑĥÑģ
    0.06
    åĽĽ
    0.06
    ieg
    0.06
    annique
    0.06
    Activations Density 0.019%

    No Known Activations