© 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. 55879
    Prev
    Next
    INDEX
    Explanations

    sequence process algorithm

    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
    apers
    -0.09
     /*#__
    -0.08
    约车
    -0.08
    计ç®Ĺåħ¬å¼ı
    -0.08
    æ¼±åı£
    -0.08
    æĸĩåĵ²
    -0.08
    åĴ¸é±¼
    -0.08
     magn
    -0.08
    رخ
    -0.07
    è¡¡
    -0.07
    POSITIVE LOGITS
    è¿ĩç¨ĭ
    0.10
     process
    0.09
    process
    0.08
    è¾Ĺ转
    0.08
     tab
    0.08
    Process
    0.08
     processo
    0.08
     sequence
    0.08
    è¿ĩç¨ĭçļĦ
    0.07
     proceso
    0.07
    Activations Density 0.003%

    No Known Activations