© 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. 21827
    Prev
    Next
    INDEX
    Explanations

    lambda function, detoxing, aloe vera, vacation club

    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
    çĻ½çŁ³
    -0.07
    IColor
    -0.07
     ÏĢά
    -0.07
    tti
    -0.07
    ÙĦاغ
    -0.07
    ãģĿãģĨãģ§ãģĻãģĮ
    -0.06
    人åĬĽèµĦæºIJ社ä¼ļä¿Ŀéļľ
    -0.06
     vong
    -0.06
    orda
    -0.06
    cling
    -0.06
    POSITIVE LOGITS
    rat
    0.06
    ctl
    0.06
    iform
    0.06
    .tw
    0.06
     Owens
    0.06
    icot
    0.06
    æĢİä¹ĪåĬŀåij¢
    0.06
     ÙĩÙĨا
    0.06
     perv
    0.06
    è¿Ļä¹Īç®Ģåįķ
    0.06
    Activations Density 0.341%

    No Known Activations