© 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. 20673
    Prev
    Next
    INDEX
    Explanations

    class, seminar, or actors

    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
    èĻļ
    -0.08
    ç»ĪæĹ¥
    -0.07
    ç¥Ŀç¦ıä½ł
    -0.07
    undler
    -0.07
    对客æĪ·
    -0.07
     unknow
    -0.07
    亲æ°ij
    -0.07
    éĽĩåijĺ
    -0.07
    downloads
    -0.07
    imgs
    -0.07
    POSITIVE LOGITS
    个åĪ«
    0.10
    åıijè¨Ģ
    0.10
    çıŃä¸Ĭ
    0.09
    带åĬ¨
    0.09
    ä¼ĺçĶŁ
    0.09
    åIJİæİĴ
    0.09
    带åĬ¨ä¸ĭ
    0.09
    çıŃéĩĮ
    0.09
    çıŃå¹²éĥ¨
    0.08
    åħ¨çıŃ
    0.08
    Activations Density 0.018%

    No Known Activations