© 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. 20489
    Prev
    Next
    INDEX
    Explanations

    duration or time period

    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
    beri
    -0.09
    endus
    -0.08
    inas
    -0.08
    çİ°åľ¨æĺ¯
    -0.08
    ä»Ĭ天æĺ¯
    -0.08
    常年
    -0.08
    æŶéĹ´ä¹ħäºĨ
    -0.08
    èĢĮæĪĺ
    -0.08
    anders
    -0.08
    ierz
    -0.08
    POSITIVE LOGITS
     ëıĻìķĪ
    0.10
    ä¹ĭåĨħ
    0.09
    åĨħçļĦ
    0.09
    ãģĨãģ¡ãģ«
    0.09
    ä¸įåıijçĶŁ
    0.08
    ëıĻìķĪ
    0.08
    ä¸įç»Ŀ
    0.07
     걸ì³IJ
    0.07
    æľŁåĨħ
    0.07
    èĮĥåĽ´åĨħ
    0.07
    Activations Density 0.046%

    No Known Activations