© 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. 24548
    Prev
    Next
    INDEX
    Explanations

    names ending in Jr. or III

    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
    mans
    -0.07
    ycl
    -0.07
    otta
    -0.07
    **”,
    -0.06
    inqui
    -0.06
    ä¾Ŀ
    -0.06
    aaa
    -0.06
    çĽĪ
    -0.06
    udas
    -0.06
    ina
    -0.06
    POSITIVE LOGITS
    /the
    0.07
    ernas
    0.07
    ÙİÙijÙĨ
    0.07
     himself
    0.07
    ündür
    0.07
    ï¸İ
    0.07
    æĽ´æĸ°æŶéĹ´
    0.07
    uner
    0.06
     aka
    0.06
    eger
    0.06
    Activations Density 0.071%

    No Known Activations