© 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. 20375
    Prev
    Next
    INDEX
    Explanations

    code examples and structure

    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
    serter
    -0.09
     ×ŀ×ĸ
    -0.07
    ä¸Ģå¥Ĺ
    -0.07
    MMMM
    -0.06
     mi
    -0.06
    _FF
    -0.06
     Anwendungen
    -0.06
    RDD
    -0.06
    äºĨä¸Ģå¥Ĺ
    -0.06
    念
    -0.06
    POSITIVE LOGITS
    ä¾ĽæĤ¨
    0.07
    itten
    0.07
    åı¯ä»¥åıĤèĢĥ
    0.07
    ä»ħä¾ĽåıĤèĢĥ
    0.07
    ä¾Ľå¤§å®¶åıĤèĢĥ
    0.07
    à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļà¸ģาร
    0.07
    ÑĩÑĥ
    0.07
    .Nullable
    0.07
    SV
    0.07
     helpful
    0.07
    Activations Density 0.006%

    No Known Activations