© 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. 57074
    Prev
    Next
    INDEX
    Explanations

    disasters and financial crises

    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
    å°ĨæĿ¥
    -0.07
    anz
    -0.07
    ä¸Ń庸
    -0.07
    èĢĮåĬªåĬĽ
    -0.07
    è¦ģç»ı常
    -0.07
    ÏĢοιη
    -0.06
    åģļäºĭæĥħ
    -0.06
    æĿ¥æĦĪ
    -0.06
    æĹ¥æĸ°æľĪå¼Ĥ
    -0.06
    çļĦåŃĺåľ¨
    -0.06
    POSITIVE LOGITS
    æ³¢åıĬ
    0.12
     unprecedented
    0.12
     widespread
    0.11
    åı²ä¸ĬæľĢ
    0.11
    åıijçĶŁäºİ
    0.11
    åıijçĶŁåľ¨
    0.10
    大éĿ¢ç§¯
    0.09
    å¼ķåıijçļĦ
    0.09
     aftermath
    0.09
    è¦ı模
    0.09
    Activations Density 0.443%

    No Known Activations