© 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. 17887
    Prev
    Next
    INDEX
    Explanations

    variable names with assignments

    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
    ÑĢоÑģ
    -0.06
    mland
    -0.05
    vard
    -0.05
    alian
    -0.05
    æ¸Īãģ¿
    -0.05
    ;d
    -0.05
    à¹Ģ
    -0.05
    ä¸į移
    -0.05
    ique
    -0.05
    ifying
    -0.05
    POSITIVE LOGITS
    elder
    0.06
    indel
    0.06
    ÙĪسÛĮ
    0.05
    ÑıÑĢ
    0.05
    зина
    0.05
    ields
    0.05
    åįģæĸ¹
    0.05
    å¤ĸ侧
    0.05
    ÙĨدر
    0.05
    éĢļ
    0.05
    Activations Density 0.023%

    No Known Activations