© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19728
    Prev
    Next
    INDEX
    Explanations

    asking you to do something

    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
    ÙĬاب
    -0.06
    走强
    -0.06
    年建
    -0.06
    çļĦåħ¨éĿ¢
    -0.06
    以任ä½ķ
    -0.06
    teria
    -0.06
    skal
    -0.06
    åľ¨æĪijçļĦ
    -0.06
    илÑĮ
    -0.06
    ä¸ĢæĿ¡é¾Ļ
    -0.06
    POSITIVE LOGITS
    hus
    0.05
    anı
    0.05
    å°ıäºĭ
    0.05
     Dy
    0.05
    ĮĢ
    0.05
    å¤įæĿĤ
    0.05
    оÑģÑĤÑĮÑİ
    0.05
    xo
    0.05
     durability
    0.05
    ä¸ĵ注
    0.05
    Activations Density 0.029%

    No Known Activations