© 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. 46843
    Prev
    Next
    INDEX
    Explanations

    .org greetings

    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
    寻
    -0.06
    иденÑĤ
    -0.06
    æIJº
    -0.06
    çķĮ
    -0.06
    éħ
    -0.06
    éĢīæĭ©åľ¨
    -0.06
    æĦıä¹īä¸ĬçļĦ
    -0.06
    å¼Ģæ°´
    -0.06
    æĭīå¼Ģåºıå¹ķ
    -0.06
    [val
    -0.06
    POSITIVE LOGITS
    onas
    0.08
    nese
    0.07
    aga
    0.07
    .strict
    0.07
    çĥ¬
    0.07
    æķħ人
    0.07
     Chess
    0.07
    èIJ¨æĸ¯
    0.07
     Há»ıa
    0.07
    lew
    0.06
    Activations Density 0.005%

    No Known Activations