© 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. 18997
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    é¡ŀ
    -0.06
     Gaul
    -0.05
    ее
    -0.05
    ial
    -0.05
    iais
    -0.05
    ä¹ł
    -0.05
    ias
    -0.05
    éĥ¨åĪĨçļĦ
    -0.05
    大éĥ¨åĪĨçļĦ
    -0.05
    ymph
    -0.05
    POSITIVE LOGITS
    ä»»
    0.06
    æ¯ı次
    0.06
    éĺĸ
    0.06
     ìĭľìŀijíĸĪëĭ¤
    0.06
    æ¯ıä¸Ģ
    0.06
    äºĮè¿ŀ
    0.06
    Ùĩر
    0.06
    æĩĤ
    0.06
    ÙĦÙĤ
    0.05
     éché
    0.05
    Activations Density 0.000%

    No Known Activations