© 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. 48519
    Prev
    Next
    INDEX
    Explanations

    social media platforms

    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
    æ°´æ´Ĺ
    -0.07
    Ø¡
    -0.07
    欲
    -0.06
    æĪIJçīĩ
    -0.06
    çīµ
    -0.06
    .scrollHeight
    -0.06
    æķĻèĤ²ç½ij
    -0.06
    æĿ¥çĶµ
    -0.06
    çĥŃæIJľè¯į
    -0.06
    è¿Ń
    -0.06
    POSITIVE LOGITS
    _blocking
    0.09
    丽èIJį
    0.08
    çļĦ建ç«ĭ
    0.08
    主è¦ģçĶŁäº§
    0.08
    åįģåħ«æĿ¡
    0.08
    ä¸ļåĬ¡å·¥ä½ľ
    0.08
    /topics
    0.08
    ican
    0.07
    æĻļå®ī
    0.07
    éĿ
    0.07
    Activations Density 0.226%

    No Known Activations