© 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. 30105
    Prev
    Next
    INDEX
    Explanations

    time series or local time

    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
    rakt
    -0.07
    DataStream
    -0.07
    æĿIJ
    -0.07
     overnight
    -0.07
    macht
    -0.07
    à¸ĺà¸ĩ
    -0.07
    æľĢå¾Įãģ¾ãģ§
    -0.07
     Overnight
    -0.07
    rades
    -0.07
    éķ¿å¹´
    -0.07
    POSITIVE LOGITS
     elapsed
    0.08
    éIJĺ
    0.07
     events
    0.07
    ä»Ģä¹Īäºĭæĥħ
    0.07
     time
    0.07
    纪
    0.07
    åħ·ä½ĵæŶéĹ´
    0.07
    زاÙħ
    0.07
     زÙħاÙĨÛĮ
    0.07
     Reign
    0.07
    Activations Density 0.001%

    No Known Activations