© 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. 20251
    Prev
    Next
    INDEX
    Explanations

    one or the other

    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
    继
    -0.05
    ssp
    -0.05
    åħ¶æŀĹ
    -0.05
    _AA
    -0.05
    asa
    -0.05
    æł¼å¼ı
    -0.05
    对åįİ
    -0.05
    itora
    -0.05
    *(-
    -0.05
    åĪĢåŃIJ
    -0.05
    POSITIVE LOGITS
    æķĻäºİ
    0.05
    éĢīæĭ©ä¸įåIJĮçļĦ
    0.05
    able
    0.05
    æĺİä¿¡
    0.05
     اÙĦباÙĦ
    0.05
    longleftrightarrow
    0.05
    ç»ıèIJ¥æ´»åĬ¨
    0.05
    ÙĪÙħÙĬØ©
    0.05
    åŀĽ
    0.05
    ØŃد
    0.05
    Activations Density 0.002%

    No Known Activations