© 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. 63734
    Prev
    Next
    INDEX
    Explanations

    [[references]]

    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
    à¸ķัว
    -0.07
    åĮħ饺åŃIJ
    -0.07
    à¹Ģà¸Ļา
    -0.06
    ardino
    -0.06
    ObjectId
    -0.06
    .bio
    -0.06
    åı·åĴĮ
    -0.06
    pha
    -0.06
     been
    -0.06
    å¾ĹäºĨ
    -0.06
    POSITIVE LOGITS
    acho
    0.08
    opyright
    0.08
     ért
    0.07
    -comments
    0.07
    äºĴ帮
    0.07
    ãģŁãģŁ
    0.07
    å±ķå¼Ģåħ¨éĥ¨
    0.07
    ä½ĵåĪ¶
    0.07
     اÙĦØ´ÙĬØ¡
    0.07
    eners
    0.07
    Activations Density 0.003%

    No Known Activations