© 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. 10868
    Prev
    Next
    INDEX
    Explanations

    $\mathbb R^n$

    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
    راÙħ
    -0.08
    åľ¨å¤§åѦ
    -0.08
    åı¯æĢľçļĦ
    -0.08
    kje
    -0.08
    ekk
    -0.07
    æĹĹé¼ĵ
    -0.07
    ([('
    -0.07
    æł¼å°Ķ
    -0.07
    aed
    -0.07
     Kenny
    -0.07
    POSITIVE LOGITS
     век
    0.08
    åIJijéĩı
    0.08
     vector
    0.08
    ä¿
    0.07
     n
    0.07
    ä¸Ģåı£
    0.07
    ï¼ĵ
    0.06
    (dim
    0.06
    åĪĴåĪĨ为
    0.06
     tá»įa
    0.06
    Activations Density 0.013%

    No Known Activations