© 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. 19965
    Prev
    Next
    INDEX
    Explanations

    `[` or `.` after data and variable names

    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
     иÑģполниÑĤелÑĮной
    -0.05
    riz
    -0.05
    ponce
    -0.05
    Äįan
    -0.05
    raid
    -0.05
    é¡Į
    -0.05
    åĪ»æĿ¿
    -0.05
    teen
    -0.05
    æ¢Ŀ
    -0.05
    ضا
    -0.05
    POSITIVE LOGITS
    خاÙĦ
    0.06
    ä¸ĭåIJĮ
    0.06
    ç»ıèIJ¥è®¸åı¯è¯ģ
    0.06
     API
    0.05
    моло
    0.05
     tel
    0.05
    anc
    0.05
    ç±
    0.05
    hyth
    0.05
    yth
    0.05
    Activations Density 0.041%

    No Known Activations