© 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. 50304
    Prev
    Next
    INDEX
    Explanations

    actions and perceptions

    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
    çļĦä¸Ģç§į
    -0.10
    çļĦä¸Ģç§įæĸ¹å¼ı
    -0.08
    æŁIJä¸Ģ天
    -0.08
    ä¸Ģ缴ä¿ĿæĮģ
    -0.08
    ä¸ĢçĽ´ä»¥
    -0.08
    çļĦä¸Ģæł·
    -0.08
    ä¸Ģ次次
    -0.08
    个åĪ«
    -0.08
    çļĦä¸Ģ種
    -0.08
     occasional
    -0.08
    POSITIVE LOGITS
    åıĪä¸Ģ
    0.10
    äºĨäºĭ
    0.09
    便èĥ½
    0.09
    便æĺ¯
    0.09
    便åı¯
    0.09
    èĢĮå·²
    0.08
    åĴĮäºĮ
    0.08
    æĪĸå¤ļ
    0.08
    便ä¼ļ
    0.08
    便被
    0.08
    Activations Density 0.047%

    No Known Activations