© 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. 24265
    Prev
    Next
    INDEX
    Explanations

    programming code structure definition

    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
    kens
    -0.08
    为èį£
    -0.07
    åĴĮéĩijèŀį
    -0.07
    flation
    -0.07
    æĢ»åĨłåĨĽ
    -0.07
    ikä
    -0.07
    æī¾åĪ°èĩªå·±
    -0.07
    常åIJĥ
    -0.07
    bery
    -0.07
    æĺĮ
    -0.07
    POSITIVE LOGITS
    presso
    0.08
    æĢ§åĴĮ
    0.07
    çĤ¹åĩ»æŁ¥çľĭ
    0.07
    lett
    0.07
    æĪĸ缴æİ¥
    0.07
    æĢ§æĪĸ
    0.06
    éĩij鸡
    0.06
    ured
    0.06
    婦
    0.06
    ([('
    0.06
    Activations Density 0.314%

    No Known Activations