© 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. 32911
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or symbols

    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
    ing
    -0.07
    ãģĦãĤĭ
    -0.06
     "
    -0.06
    ibat
    -0.06
    als
    -0.06
    ington
    -0.06
    s
    -0.06
    aan
    -0.06
    INGTON
    -0.06
    ffect
    -0.06
    POSITIVE LOGITS
    .:**
    0.09
    Ģ
    0.09
    taki
    0.09
     à¸ķà¸²à¸¡à¸Ľà¸£à¸°à¹Ģà¸łà¸Ĺ
    0.09
     à¸ķามระà¸Ķัà¸ļ
    0.09
    зеÑĨ
    0.08
    wass
    0.08
    æł¼æĭī
    0.08
    ��
    0.08
     -**
    0.08
    Activations Density 0.038%

    No Known Activations