© 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. 26356
    Prev
    Next
    INDEX
    Explanations

    women with disabilities, social media

    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
    aze
    -0.07
    uld
    -0.07
    istro
    -0.07
    agni
    -0.07
     Vidal
    -0.06
    isis
    -0.06
    asia
    -0.06
    abel
    -0.06
    arge
    -0.06
    asen
    -0.06
    POSITIVE LOGITS
     certain
    0.08
    èĽŁ
    0.08
    /native
    0.08
    å°±ä¸Ģå®ļè¦ģ
    0.07
    tures
    0.07
     Kai
    0.07
     ÑĦизиÑĩеÑģкой
    0.07
    èĸĩ
    0.07
    ì¹´ìĿ´
    0.07
    æĥľ
    0.07
    Activations Density 0.885%

    No Known Activations