© 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. 22553
    Prev
    Next
    INDEX
    Explanations

    species, drugs, and diseases

    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
    çīĪ
    -0.07
    ibl
    -0.07
    æĹłè®ºæĺ¯åľ¨
    -0.07
    ä¸ŃåĴĮ
    -0.07
    çīĪæĿĥå½Ĵ
    -0.07
    ä¸įåIJĮçļĦ人
    -0.07
    çīĪçļĦ
    -0.07
    å»
    -0.07
    æĴ
    -0.07
     equivalent
    -0.07
    POSITIVE LOGITS
    管çIJĨç±»
    0.08
    è¿Ļç±»
    0.08
    åĥı
    0.08
    æľīäºĽäºĭ
    0.08
     whose
    0.08
    ç±»çŃī
    0.08
    infeld
    0.08
    大å®Ĺ
    0.07
    åĨ·éŨ
    0.07
    大å¤ļæķ°
    0.07
    Activations Density 0.408%

    No Known Activations