© 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. 57247
    Prev
    Next
    INDEX
    Explanations

    page /system ard Geometry high (default per Line

    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
     desto
    -0.07
    äºĨåIJĹ
    -0.07
    æĶ¯æĮģä¸İ
    -0.06
    æѤè¡Į
    -0.06
    _HAL
    -0.06
    ÑĤиви
    -0.06
     übrigens
    -0.06
    ema
    -0.06
    äºİå¿ĥ
    -0.06
    æĻ¨æĬ¥
    -0.06
    POSITIVE LOGITS
    秫
    0.07
    ),$
    0.07
    ���
    0.06
    ��
    0.06
    \\/
    0.06
    EIF
    0.06
    å¦
    0.06
    صر
    0.06
    пл
    0.06
    tright
    0.06
    Activations Density 0.305%

    No Known Activations