© 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. 2480
    Prev
    Next
    INDEX
    Explanations

    adduction / appellee

    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
    çĭ¬ç«ĭ
    -0.11
    çĭ¬ç«ĭçļĦ
    -0.10
    çĸı
    -0.09
     independence
    -0.09
     independent
    -0.09
    Independent
    -0.09
     ëıħ립
    -0.09
    çĭ¬ç«ĭå®ĮæĪIJ
    -0.09
    dry
    -0.09
     Independent
    -0.09
    POSITIVE LOGITS
    稳
    0.11
    æ³¥æ³ŀ
    0.09
    ä¸ĭæ²ī
    0.09
    æ¿¡
    0.09
    é»ı
    0.09
    湿
    0.09
    温æļĸ
    0.09
    ç²ĺ稳
    0.08
    软åĮĸ
    0.08
    æ´¼
    0.08
    Activations Density 0.435%

    No Known Activations