© 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. 48385
    Prev
    Next
    INDEX
    Explanations

    depending on

    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
    颱
    -0.06
    åIJĮæĹ¥
    -0.06
    à¸ļ
    -0.06
    ogna
    -0.06
     timespec
    -0.06
    åħĭåĬĽ
    -0.06
    çļĦè¯Ŀ
    -0.06
    注æĦıçĤ¹
    -0.06
    æĺ¥æĹ¥
    -0.06
    籤
    -0.06
    POSITIVE LOGITS
    lessly
    0.08
    inia
    0.07
    arters
    0.07
    ä¸ĢæĿ¡è¡Ĺ
    0.07
    nic
    0.07
    ÙĨدÙĨ
    0.07
    pto
    0.07
    :[
    0.07
     Nº
    0.07
    ئر
    0.07
    Activations Density 0.236%

    No Known Activations