© 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. 12686
    Prev
    Next
    INDEX
    Explanations

    heat and summer weather

    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
    éĽªä¸Ń
    -0.08
    _INTERFACE
    -0.08
     Matchers
    -0.08
    ç±»é£İ湿
    -0.08
    é£İéĽª
    -0.07
    åľ£è¯ŀ
    -0.07
    æĺ¥èģĶ
    -0.07
    éķ¿çĻ½å±±
    -0.07
    è·¤
    -0.07
     Asturias
    -0.07
    POSITIVE LOGITS
    å¤ıåŃ£
    0.18
     summer
    0.18
    çĤİçĥŃ
    0.18
    å¤ıæĹ¥
    0.18
    æļij
    0.18
    å¤ı
    0.18
    éĺ²æļij
    0.17
    summer
    0.17
    é«ĺ温
    0.17
    éħ·æļij
    0.17
    Activations Density 0.258%

    No Known Activations