© 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. 26808
    Prev
    Next
    INDEX
    Explanations

    energy measurements

    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
    æĮĩæķ¸
    -0.08
    ä»Ģä¹Īæł·çļĦ人
    -0.08
    ä¸ĩ亩
    -0.07
    spf
    -0.07
    伸åĩºæīĭ
    -0.07
    èįŁ
    -0.07
    éķ¿éĿĴ
    -0.07
    æ·ij
    -0.07
    æĮĩæķ°
    -0.07
    area
    -0.07
    POSITIVE LOGITS
     precise
    0.08
     released
    0.08
    åĬłä¸Ĭ
    0.08
     minus
    0.08
    released
    0.07
     nominal
    0.07
    æī£éĻ¤
    0.07
    精确
    0.07
     Released
    0.07
    åĩıåİ»
    0.07
    Activations Density 0.005%

    No Known Activations