© 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. 17629
    Prev
    Next
    INDEX
    Explanations

    single

    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¯ıå¼ł
    -0.07
    缸åħ³æݨèįIJ
    -0.07
    åĹĵåŃIJ
    -0.07
    .online
    -0.07
    -Smith
    -0.07
    åѤå¯Ĥ
    -0.07
    ç²¾è¯ļ
    -0.07
     sophistication
    -0.07
    æ¿Ģ
    -0.06
    áĥIJáĥķ
    -0.06
    POSITIVE LOGITS
    ادÛĮ
    0.08
    emp
    0.08
    å¿«å¿«ä¹IJ
    0.08
     sublic
    0.08
    ovel
    0.07
    à¸ķà¹Ī
    0.07
     bonds
    0.07
    empa
    0.07
    CHK
    0.07
    adt
    0.07
    Activations Density 0.003%

    No Known Activations