© 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. 27316
    Prev
    Next
    INDEX
    Explanations

    physical or scientific terms

    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
    å¾Ĺä¸Ĭ
    -0.08
    èµ°ä¸Ĭ
    -0.08
     Ingr
    -0.07
    çĴĢ
    -0.07
    .paths
    -0.07
    ä¸İ大
    -0.07
    ียà¸ĩ
    -0.07
    emor
    -0.06
    æĶ¾ç¼ĵ
    -0.06
    weg
    -0.06
    POSITIVE LOGITS
    leck
    0.08
     dividing
    0.08
     locations
    0.08
    æīĢåľ¨çļĦä½įç½®
    0.08
    åľ¨åĵªéĩĮ
    0.07
    æīĢåľ¨ä½įç½®
    0.07
    lacer
    0.07
    /null
    0.07
     Locations
    0.07
    å¤ĦçļĦ
    0.07
    Activations Density 0.001%

    No Known Activations