© 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. 56962
    Prev
    Next
    INDEX
    Explanations

    copyright notices and licensing

    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
    红åı¶
    -0.07
    åįĹåĮº
    -0.07
    ypi
    -0.07
    winner
    -0.06
    urch
    -0.06
    åįİå°Ķ
    -0.06
    举éĺ³
    -0.06
    kini
    -0.06
     econ
    -0.06
    legg
    -0.06
    POSITIVE LOGITS
    avance
    0.08
    éķ¿åģĩ
    0.07
    sock
    0.07
    èĻİ
    0.07
    idir
    0.07
    outing
    0.07
    åľŁæľ¨
    0.07
    utant
    0.07
     اÙĦÙĨÙħ
    0.07
    ç¹ģ
    0.07
    Activations Density 0.002%

    No Known Activations