© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48869
    Prev
    Next
    INDEX
    Explanations

    quantum theory and mechanics

    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
    æĦıæĥ³
    -0.08
    ighton
    -0.08
    æħ§èģª
    -0.08
    æ»ĭäºĭ
    -0.07
    Occurred
    -0.07
    人ä¸Ń
    -0.07
    æ°¸ä¹ħæĢ§
    -0.07
    æĶ¶éĽĨçļĦ
    -0.07
    FormItem
    -0.07
    æ§
    -0.07
    POSITIVE LOGITS
     theory
    0.10
    æŀ¶æŀĦ
    0.09
    ä¸ŃçļĦåľ°ä½į
    0.09
     models
    0.09
    ä½ĵç³»
    0.09
     model
    0.08
     framework
    0.08
    é«Ķç³»
    0.08
    çIJĨ论
    0.08
    ä½ĵç³»åĴĮ
    0.08
    Activations Density 0.036%

    No Known Activations