© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18653
    Prev
    Next
    INDEX
    Explanations

    end of the day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    habit
    -0.05
    itar
    -0.05
     habit
    -0.05
    yr
    -0.05
    è·¯ä¸Ĭ
    -0.05
    äºĭæĪIJ
    -0.05
    API
    -0.05
    尾巴
    -0.05
     indefinite
    -0.05
    STEM
    -0.05
    POSITIVE LOGITS
    æ¯ķç«Łæĺ¯
    0.06
    åĪ«å¿ĺäºĨ
    0.06
    кеÑĤ
    0.06
     ÑĤаки
    0.06
    è¿ĺæĺ¯ä¸Ģ个
    0.06
    goog
    0.06
    é¦ĸåħĪæĺ¯
    0.06
     bersangkutan
    0.06
     superior
    0.06
    åIJĮæł·æĺ¯
    0.06
    Activations Density 0.042%

    No Known Activations