© 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. 21814
    Prev
    Next
    INDEX
    Explanations

    EtX, hydro, car, for

    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
    ivil
    -0.06
    צ×Ļ×Ŀ
    -0.05
    æł·çļĦ
    -0.05
    çĶ¨äºİ
    -0.05
    ä¸ĸçķĮä¸Ń
    -0.05
    è¿Ļ对äºİ
    -0.05
    ivot
    -0.05
    财产æįŁå¤±
    -0.05
    esten
    -0.05
     Gim
    -0.05
    POSITIVE LOGITS
    ÙĥÙĩ
    0.06
    ogne
    0.06
    ora
    0.06
    ijske
    0.05
    ÑĪло
    0.05
    klas
    0.05
    é»ĺ
    0.05
    unk
    0.05
    éļIJ身
    0.05
    ä¼ļåijĺæľįåĬ¡
    0.05
    Activations Density 0.053%

    No Known Activations