© 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. 14908
    Prev
    Next
    INDEX
    Explanations

    abstract

    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
    lier
    -0.08
    ä¸įæĹ©
    -0.08
    oa
    -0.08
    acap
    -0.07
    Į¨
    -0.07
    ä¸Ĭå°ıåѦ
    -0.07
    ÙĪرÙĩا
    -0.07
    deutsch
    -0.07
    elm
    -0.07
    criptors
    -0.07
    POSITIVE LOGITS
     bê
    0.07
    éĩį建
    0.07
    ruz
    0.07
    erus
    0.06
    _EXTENSIONS
    0.06
    .gc
    0.06
    åIJĥä¸į
    0.06
     rebuild
    0.06
    欣
    0.06
    山人
    0.06
    Activations Density 0.011%

    No Known Activations