© 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. 62922
    Prev
    Next
    INDEX
    Explanations

    independent, independence, disjoint

    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
    缺ä¸Ģ
    -0.08
    ãĤ½ãĥ¼
    -0.07
     pay
    -0.07
    æĢ»ä¸įèĥ½
    -0.07
    æĪIJäºĨä¸Ģ个
    -0.06
     Limited
    -0.06
     gl
    -0.06
    pay
    -0.06
    éĻIJéĩı
    -0.06
     rather
    -0.06
    POSITIVE LOGITS
    çĭ¬ç«ĭæĢ§
    0.15
    çĭ¬ç«ĭ
    0.14
     independence
    0.14
    Independ
    0.13
     Independence
    0.13
    çį¨ç«ĭ
    0.13
    çĭ¬ç«ĭçļĦ
    0.12
     Independ
    0.12
     незавиÑģ
    0.12
     independencia
    0.11
    Activations Density 0.012%

    No Known Activations