© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58250
    Prev
    Next
    INDEX
    Explanations

    code and math syntax elements

    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
    ĵĴ
    -0.09
    æµ®çĶŁ
    -0.08
    è´¹çĶ¨çĶ±
    -0.08
    ạp
    -0.08
    riba
    -0.08
    çĴĢ
    -0.07
    rips
    -0.07
    onnier
    -0.07
    èİ·èµŀ
    -0.07
    ä¸Ĭè¿Ľ
    -0.07
    POSITIVE LOGITS
    å®Ī
    0.08
    éļı
    0.07
    ç¡®
    0.07
    å¾Ĵ
    0.06
    çĭ¬
    0.06
    æŁ¥æ¼ı补缺
    0.06
    çķĮ
    0.06
    vestig
    0.06
    æĪ
    0.06
    ë§IJ
    0.06
    Activations Density 0.003%

    No Known Activations