© 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. 43530
    Prev
    Next
    INDEX
    Explanations

    .sourceforge.net license

    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
    erts
    -0.08
    åįĥå±±
    -0.08
    ÙħاÙĨ
    -0.07
    亲åĴĮ
    -0.07
    alian
    -0.07
    .removeListener
    -0.07
    -bo
    -0.07
    nung
    -0.07
    [url
    -0.07
    zik
    -0.07
    POSITIVE LOGITS
    常åĬ¡å§Ķåijĺä¼ļ
    0.08
    æĪij社
    0.07
    ÙĬدة
    0.06
     Motors
    0.06
    åģ¿ä»ĺ
    0.06
    toon
    0.06
    анее
    0.06
    人æĦı
    0.06
    _strerror
    0.06
    OLI
    0.06
    Activations Density 0.007%

    No Known Activations