© 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. 11945
    Prev
    Next
    INDEX
    Explanations

    class inheritance and implementation

    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
    çļĦè¿ĺæĺ¯
    -0.07
    äºĨåIJĹ
    -0.06
    çļĦä¸Ģç³»åĪĹ
    -0.06
    ä¸Ģç³»åĪĹ
    -0.06
     pro
    -0.06
    çļĦä¸Ģå®ļ
    -0.06
     "
    -0.06
    .
    -0.06
    忱
    -0.06
    ä¸ĢèĬĤ
    -0.06
    POSITIVE LOGITS
     (){
    0.09
    rolet
    0.08
    âĨĵâĨĵ
    0.08
    ]>
    0.08
     ():
    0.08
    обен
    0.08
    mainen
    0.08
    ’:
    0.08
    漫漫
    0.08
    ”âĢ¦
    0.07
    Activations Density 0.275%

    No Known Activations