© 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. 19951
    Prev
    Next
    INDEX
    Explanations

    unordered sequences, sorting order

    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
    retta
    -0.06
    伦
    -0.05
     Barb
    -0.05
    åįļ
    -0.05
    伤害
    -0.05
    贪污
    -0.05
    tober
    -0.05
    arters
    -0.05
    åºĶæĢ¥ç®¡çIJĨå±Ģ
    -0.05
    å¤ļåIJĥ
    -0.05
    POSITIVE LOGITS
     whichever
    0.08
     unordered
    0.07
    æĹłåºı
    0.07
     alphabetical
    0.06
    alphabet
    0.06
    æľīåºıçļĦ
    0.06
    unordered
    0.06
    attaa
    0.06
    order
    0.06
    sorted
    0.06
    Activations Density 0.056%

    No Known Activations