© 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. 18055
    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
    å¸ĿçļĦ
    -0.06
    æĹłéĹ»
    -0.06
    顺åºĶ
    -0.05
     ÙģعÙĦÙĬ
    -0.05
    ern
    -0.05
    rita
    -0.05
    beck
    -0.05
    è¦ģ
    -0.05
     lom
    -0.05
    usak
    -0.05
    POSITIVE LOGITS
    شات
    0.06
     malam
    0.06
     special
    0.06
    åºĬä¸Ĭ
    0.06
    ä¹Łå¾Īå¤ļ
    0.06
    å¸ĥå±ĢåĴĮ
    0.06
    çļĦ设置
    0.05
    ä¸įä½ı
    0.05
    lub
    0.05
    odon
    0.05
    Activations Density 0.000%

    No Known Activations