© 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. 3713
    Prev
    Next
    INDEX
    Explanations

    united states court of appeals circuits

    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
    utang
    -0.08
    æķ£
    -0.07
    çĦī
    -0.07
    à¦ļà§ĩ
    -0.07
    éķĩæĶ¿åºľ
    -0.07
    ummings
    -0.07
     Smithsonian
    -0.07
     пÑĢиÑijм
    -0.06
     Schweizer
    -0.06
    lda
    -0.06
    POSITIVE LOGITS
    èµĽåĮº
    0.08
    åľ°åĮº
    0.08
    åľ°åįĢ
    0.08
     populous
    0.08
    åľ°åĮºçļĦ
    0.08
    åĶ¯ä¸Ģä¸Ģ家
    0.08
     regions
    0.08
     vá»±c
    0.08
    åľ°åĮºåĴĮ
    0.08
     branch
    0.08
    Activations Density 0.635%

    No Known Activations