© 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. 50066
    Prev
    Next
    INDEX
    Explanations

    programming syntax related to data and variables

    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
    çIJĨä¼ļ
    -0.06
    çľĭåĪ°æĪij
    -0.06
    为人æ°ij
    -0.06
    人æĿ¥è¯´
    -0.06
     RuntimeError
    -0.06
    assy
    -0.06
    ave
    -0.06
    dep
    -0.06
    çļĦ人æĿ¥è¯´
    -0.06
    aman
    -0.06
    POSITIVE LOGITS
    ä¸Ģå¤ķ
    0.08
    sprozess
    0.07
    à¸Ńà¸ģ
    0.07
    ä¸įå¾Ĺ
    0.07
    lobber
    0.07
    chini
    0.07
    å¹´å§ĭ
    0.07
    åıĹ
    0.07
    InitialState
    0.07
    èĭ¥æľī
    0.06
    Activations Density 0.086%

    No Known Activations