© 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. 21708
    Prev
    Next
    INDEX
    Explanations

    .com or code judges

    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
    åħį费注åĨĮ
    -0.07
    å¼±çĶµ
    -0.07
     intele
    -0.07
    就象
    -0.07
    å½ĵ羣
    -0.07
    æĢ§äº¤
    -0.07
    家æĶ¿
    -0.07
    èĿ¶
    -0.07
    åĪ°å¤©
    -0.07
     seder
    -0.07
    POSITIVE LOGITS
    æĿĢ人
    0.07
    ç«ĭå¾·æłij人
    0.06
    å¼Ģ课
    0.06
    ets
    0.06
    为大家带æĿ¥
    0.06
    Mine
    0.06
     punishments
    0.06
    (stdin
    0.06
     submissions
    0.06
     sandbox
    0.06
    Activations Density 0.030%

    No Known Activations