© 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. 11976
    Prev
    Next
    INDEX
    Explanations

    loop bounds

    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
    lec
    -0.08
    воло
    -0.08
    =?,
    -0.07
    zzle
    -0.07
    æ°¸è¿ľçļĦ
    -0.07
    æĸĩåĮĸçŁ¥è¯Ĩ
    -0.07
    ìŀĺ
    -0.07
    optic
    -0.07
    meg
    -0.07
    ","","
    -0.06
    POSITIVE LOGITS
    arder
    0.07
     Aper
    0.07
    ultiple
    0.07
    ĸī
    0.06
    é¼İé¼İ
    0.06
    flutter
    0.06
    addon
    0.06
     vén
    0.06
    LowerCase
    0.06
    arik
    0.06
    Activations Density 0.008%

    No Known Activations