© 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. 33179
    Prev
    Next
    INDEX
    Explanations

    main function or method

    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
    geries
    -0.08
     sourceMapping
    -0.08
    æĻĵå¾Ĺ
    -0.07
    -opacity
    -0.07
    满æľĪ
    -0.07
    ä¸ĭä¸Ģç§Ĵ
    -0.07
    微波
    -0.07
    èµĦæĸĻä¸ĭè½½
    -0.07
    åıĪæĢķ
    -0.07
     Kabar
    -0.07
    POSITIVE LOGITS
    antai
    0.07
    ä¸Ńæ·»åĬł
    0.07
    æĢ
    0.07
    iverse
    0.07
    æĮģ
    0.07
    æĹłéĻIJçļĦ
    0.06
    å®īåħ¨è´£ä»»
    0.06
    .main
    0.06
    -less
    0.06
    AZE
    0.06
    Activations Density 0.142%

    No Known Activations