© 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. 16947
    Prev
    Next
    INDEX
    Explanations

    Olympia Hall

    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
    otos
    -0.06
    èį§
    -0.05
    escu
    -0.05
    sl
    -0.05
    urch
    -0.05
    æĪª
    -0.05
    zir
    -0.05
    ä¸įéĢĢ
    -0.05
    ãm
    -0.05
    ä¸Ģå¸Ĩ
    -0.05
    POSITIVE LOGITS
    closest
    0.06
    جÙĩ
    0.06
    ATAB
    0.06
     dormitórios
    0.06
    说æĪij
    0.06
     बà¥ģ
    0.06
    ÑĩаÑİÑĤ
    0.05
    +)/
    0.05
    _mo
    0.05
     spelled
    0.05
    Activations Density 0.001%

    No Known Activations