© 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. 11576
    Prev
    Next
    INDEX
    Explanations

    chromosome sequences

    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
    好
    -0.08
    ANNER
    -0.08
    öll
    -0.07
    åĿĬ
    -0.06
    .constant
    -0.06
     co
    -0.06
    æĦıè¯ĨåĴĮ
    -0.06
    å¥½åľ¨
    -0.06
    社ä¼ļåĴĮ
    -0.06
    é£İéĻ©åĪĨæŀIJ
    -0.06
    POSITIVE LOGITS
    orada
    0.08
    orado
    0.08
     whichever
    0.08
    ç½Ĺå¾·
    0.08
    gable
    0.08
    acz
    0.07
    äºĶæĹ¥
    0.07
    erat
    0.07
    该åĮº
    0.07
    åĵªä¸Ģ个
    0.07
    Activations Density 0.136%

    No Known Activations