© 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. 18014
    Prev
    Next
    INDEX
    Explanations

    acute illnesses

    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
    çĥŃæĥħåĴĮ
    -0.06
    ç½®
    -0.06
    mêmes
    -0.06
     plu
    -0.06
    linge
    -0.06
    è¿ĩä¸Ģ次
    -0.06
    RACT
    -0.06
    çĥŃæĥħ
    -0.06
    çīĩåŃIJ
    -0.05
    ylim
    -0.05
    POSITIVE LOGITS
    å©´å¹¼åĦ¿
    0.08
    å¹¼åĦ¿åĽŃ
    0.07
    幼年
    0.07
    åѦé¾Ħ
    0.06
    å¹¼åĦ¿
    0.06
    aya
    0.06
     minors
    0.06
    สำหรัà¸ļà¹Ģà¸Ķà¹ĩà¸ģ
    0.06
    ä¸Ńå°ıä¼ģä¸ļ
    0.06
    æľªæĪIJå¹´
    0.06
    Activations Density 0.262%

    No Known Activations