© 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. 64123
    Prev
    Next
    INDEX
    Explanations

    energy and fuel metabolism

    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
    spy
    -0.07
     discret
    -0.07
    roit
    -0.07
     impun
    -0.07
    å¼ĢåĪ°
    -0.07
    ä¹ĭ声
    -0.07
    incid
    -0.07
    asten
    -0.07
    以èĩ´
    -0.07
    .prepend
    -0.06
    POSITIVE LOGITS
    ä¾Ľ
    0.11
    ä¾ĽåºĶ
    0.10
    ä¾Ľç»Ļ
    0.10
    转åĮĸæĪIJ
    0.09
    åĤ¨åŃĺ
    0.09
    æĸ°éĻĪ代谢
    0.09
     Converted
    0.09
     sust
    0.09
    代谢
    0.09
     поÑģÑĤÑĥп
    0.09
    Activations Density 0.026%

    No Known Activations