© 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. 21231
    Prev
    Next
    INDEX
    Explanations

    Copyright notices

    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
    å¦Ĥ约
    -0.05
    iffe
    -0.05
    schw
    -0.05
    åĨįä¸į
    -0.05
    æİ¥ä¸ĭ
    -0.05
    çĮ¿
    -0.05
    ibbon
    -0.05
    keh
    -0.05
    гÑĢам
    -0.05
    ä¸ĢåĽŀ
    -0.05
    POSITIVE LOGITS
    acar
    0.06
    åĴĮæĪij
    0.06
    Æ¡i
    0.05
    å¾Ģ
    0.05
    æĺİ天çļĦ
    0.05
    à¸Ĥà¸Ńà¸ĩà¹Ĥลà¸ģ
    0.05
     afectados
    0.05
    åIJijæĪij
    0.05
     kest
    0.05
    )':
    0.05
    Activations Density 0.187%

    No Known Activations