© 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. 8059
    Prev
    Next
    INDEX
    Explanations

    new posts

    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
     ÐłÐµÐºÐ¾Ð¼ÐµÐ½Ð´Ñĥем
    -0.09
    åĪ«æĹł
    -0.08
    ä¸Ģ个åı«
    -0.07
    æĸ°ä¹¦æݨèįIJ
    -0.07
    dirname
    -0.07
    oin
    -0.07
    gnore
    -0.07
    Ö¼
    -0.07
    erot
    -0.07
    æĢİä¹ĪåĬŀ
    -0.07
    POSITIVE LOGITS
    åħ¶ä»ĸ人
    0.07
    æĪijæĺ¯ä¸Ģ个
    0.07
     myself
    0.07
    湧
    0.07
     posting
    0.07
    æĪijå°±ä¸į
    0.07
    åĽłä¸ºæĪij
    0.07
    åģ¥åħ¨
    0.06
    æ¯ĶæĪij
    0.06
     Forums
    0.06
    Activations Density 1.910%

    No Known Activations