© 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. 25687
    Prev
    Next
    INDEX
    Explanations

    social welfare and security programs

    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
     serp
    -0.07
    çº
    -0.06
    è¿Ŀæ³ķæīĢå¾Ĺ
    -0.06
    宫é¢Ī
    -0.06
    iami
    -0.06
    èn
    -0.06
    (ctrl
    -0.06
     favicon
    -0.06
     SEO
    -0.06
     ASCII
    -0.06
    POSITIVE LOGITS
    社ä¼ļä¿Ŀéļľ
    0.12
    ç¦ıåĪ©
    0.11
    社ä¼ļç¦ıåĪ©
    0.11
    ä¿Ŀéļľ
    0.11
    åĴĮ社ä¼ļä¿Ŀéļľ
    0.11
     welfare
    0.11
     pensions
    0.10
     pension
    0.10
    çļĦä¿Ŀéļľ
    0.10
    æİ¥ç»Ń
    0.10
    Activations Density 0.091%

    No Known Activations