© 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. 1652
    Prev
    Next
    INDEX
    Explanations

    searching and googling

    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
    cak
    -0.08
    anches
    -0.08
    ={({
    -0.08
    ÙĬاس
    -0.08
    erness
    -0.08
    æĸĩ书
    -0.08
    ä¸įè¿ĩæĿ¥
    -0.08
    noz
    -0.08
    تÙĨا
    -0.08
    转载请注æĺİ
    -0.08
    POSITIVE LOGITS
    ÙĩاÛĮ
    0.06
    cht
    0.06
    rial
    0.06
    ay
    0.06
    èĩ´å¯Į
    0.06
    s
    0.06
    ili
    0.06
    å¸ĮæľĽ
    0.06
    èĩ³
    0.06
    -l
    0.06
    Activations Density 0.028%

    No Known Activations