© 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. 22723
    Prev
    Next
    INDEX
    Explanations

    approach, data, method, abnormalities, interactions

    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
    ิà¹īà¸ĩ
    -0.07
    ·
    -0.06
    é«ĺæĺİ
    -0.06
    ứt
    -0.06
    duct
    -0.06
     naw
    -0.06
    inand
    -0.06
     particular
    -0.06
    æ¯įçļĦ
    -0.06
    ather
    -0.06
    POSITIVE LOGITS
    çļĦè¿ĻäºĽ
    0.11
    çļĦè¿Ļä¸Ģ
    0.10
    çļĦè¿Ļç§į
    0.10
    çļĦè¿Ļ个
    0.09
     nÃły
    0.09
    this
    0.09
    è¿Ļæł·è¯´
    0.08
     ÑįÑĤим
    0.08
    these
    0.08
     ìĿ´ì²ĺëŁ¼
    0.08
    Activations Density 0.527%

    No Known Activations