© 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. 16006
    Prev
    Next
    INDEX
    Explanations

    about supposed to be

    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
    åıĮèĤ©
    -0.07
    åIJĮ声
    -0.06
    exceptions
    -0.06
    ä¸įåıijçĶŁ
    -0.06
     Kampus
    -0.06
    bourg
    -0.06
    ä¸ĢæĿ¡æĿ¡
    -0.06
    /extensions
    -0.06
     disappoint
    -0.06
    .exception
    -0.06
    POSITIVE LOGITS
    é½
    0.09
    çŀ»
    0.08
    åIJĪ并
    0.08
     cele
    0.07
     aps
    0.07
     perp
    0.07
    tij
    0.07
    åĤ¾
    0.07
    pus
    0.07
     há»Ĺn
    0.07
    Activations Density 0.002%

    No Known Activations