© 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. 42299
    Prev
    Next
    INDEX
    Explanations

    import statements

    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
     Cire
    -0.08
    ardy
    -0.08
    åijIJ
    -0.07
    addChild
    -0.07
    åĺĮ
    -0.07
    BitConverter
    -0.07
     [=[
    -0.07
    érc
    -0.07
     Ø£ÙĨت
    -0.07
    _pickle
    -0.07
    POSITIVE LOGITS
    HING
    0.07
    ateg
    0.07
    rouw
    0.06
     swe
    0.06
    æŀĦ
    0.06
    eki
    0.06
     Trip
    0.06
    ichi
    0.06
    rus
    0.06
     Herr
    0.06
    Activations Density 0.033%

    No Known Activations