© 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. 48675
    Prev
    Next
    INDEX
    Explanations

    legal and technical documents

    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
    ÙĬÙĩ
    -0.08
    å°ijçļĦ
    -0.06
    äºĮåŃĹ
    -0.06
     means
    -0.06
    æ´»åĬ¨æĢ»ç»ĵ
    -0.06
    ä¸ĢæŶéĹ´
    -0.06
    ä»Ģä¹ĪæĦıæĢĿ
    -0.06
    ä¹ĭäºĭ
    -0.06
    ãģ¨ãĤĤ
    -0.06
    æĹłä¸į
    -0.06
    POSITIVE LOGITS
    çļĦ第
    0.12
    第
    0.10
     nowhere
    0.09
    令第
    0.09
    åľ¨ç¬¬
    0.09
    年第
    0.08
    enheim
    0.08
    .setItem
    0.08
    åĬłåħ³æ³¨
    0.08
    ovsky
    0.08
    Activations Density 0.244%

    No Known Activations