© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22045
    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
    纳ç¨İ人è¯ĨåĪ«åı·
    -0.06
    еÑģÑĤа
    -0.06
    ä½ĵç³»åĴĮ
    -0.06
     Daarna
    -0.06
    istrib
    -0.06
    óny
    -0.06
    entif
    -0.06
    endet
    -0.06
    身份çļĦ
    -0.06
    igue
    -0.06
    POSITIVE LOGITS
    ide
    0.06
    ÚĨÙĩ
    0.05
    æĿIJ
    0.05
     Wir
    0.05
    ils
    0.05
     phu
    0.05
    jun
    0.05
    ä¸ĢåĬ¨
    0.05
    ^
    0.05
    çĭĢ
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.