© 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. 21810
    Prev
    Next
    INDEX
    Explanations

    compounds network connectivity

    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
    åĨĴ
    -0.07
    éĢĨæµģ
    -0.07
    è¿Ļ段æŶéĹ´
    -0.07
    æŁIJ天
    -0.06
    iou
    -0.06
    è¿ijæľŁçļĦ
    -0.06
    ivit
    -0.06
    缣
    -0.06
    heit
    -0.06
    çĻ»
    -0.06
    POSITIVE LOGITS
    ç»ĵæŀĦä¸Ń
    0.09
    å½¼æѤçļĦ
    0.08
    å½¼æѤ
    0.08
    åĽĽéĿ¢
    0.08
    éĿ¢å¯¹éĿ¢
    0.08
    ç»´ç³»
    0.08
    è¿ŀæİ¥çļĦ
    0.08
     connectivity
    0.08
     linking
    0.08
    å½¢æĪIJäºĨ
    0.08
    Activations Density 0.094%

    No Known Activations