© 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. 63854
    Prev
    Next
    INDEX
    Explanations

    years. Applicable law

    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
    inals
    -0.08
    ỡ
    -0.07
    itti
    -0.07
    Ý
    -0.07
    дÑĢи
    -0.07
    èIJ½çļĦ
    -0.06
     chÆ°
    -0.06
    plx
    -0.06
    WAR
    -0.06
    soever
    -0.06
    POSITIVE LOGITS
    示
    0.08
    æīĢè°ĵ
    0.07
    åĪ©
    0.07
     Gre
    0.07
    ä¸Ģä¸ªåĽ½å®¶
    0.07
    linky
    0.07
     @(
    0.06
    ipse
    0.06
    麦
    0.06
    约å®ļçļĦ
    0.06
    Activations Density 0.221%

    No Known Activations