© 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. 16262
    Prev
    Next
    INDEX
    Explanations

    constant mass and conservation

    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
    ÅĽnie
    -0.07
     Unabhäng
    -0.07
    Independ
    -0.07
    ä¸½å¨ľ
    -0.07
    约èĢĮåIJĮ
    -0.07
    éĹ´è·Ŀ
    -0.07
    åĪ°åĮĹ京
    -0.07
    ite
    -0.07
    çĭ¬ç«ĭçļĦ
    -0.07
    ä½Ĩä¸įéĻIJäºİ
    -0.07
    POSITIVE LOGITS
    å®ĪæģĴ
    0.11
    æĢ»éĩı
    0.10
     conservation
    0.09
    æĢ»é¢Ŀ
    0.09
    æĢ»åĢ¼
    0.08
     conserve
    0.08
     conserv
    0.08
     Gesamt
    0.08
     overall
    0.08
    æĢ»éĩıçļĦ
    0.08
    Activations Density 0.006%

    No Known Activations