© 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. 16000
    Prev
    Next
    INDEX
    Explanations

    high intensity and scale

    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
    eprom
    -0.08
    æł·çļĦ
    -0.08
    对çĹĩä¸ĭèį¯
    -0.08
    磶
    -0.08
    æ±Ĥç²¾
    -0.08
    å¼ıåĴĮ
    -0.08
    æĺ¥æļĸ
    -0.07
    -rounded
    -0.07
    apsed
    -0.07
    gression
    -0.07
    POSITIVE LOGITS
     enough
    0.10
     (>
    0.09
     (<
    0.09
     جداÙĭ
    0.08
     جدÙĭا
    0.08
     genug
    0.08
    -scale
    0.08
    -range
    0.07
    /high
    0.07
    (<
    0.07
    Activations Density 0.235%

    No Known Activations