© 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. 20962
    Prev
    Next
    INDEX
    Explanations

    file extensions

    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
    apan
    -0.06
    .defaults
    -0.06
    Impl
    -0.05
    (Pos
    -0.05
    Stamped
    -0.05
    ç·Ĭ
    -0.05
    Maker
    -0.05
    èİ·åıĸæĽ´å¤ļ
    -0.05
    maker
    -0.05
    çĶ·å¥³
    -0.05
    POSITIVE LOGITS
    æĥħå½¢ä¹ĭä¸ĢçļĦ
    0.06
    ishi
    0.05
     nome
    0.05
    è¿ŀåIJĮ
    0.05
    áĢĻáĢºáĢ¸
    0.05
    åIJįçļĦ
    0.05
     kin
    0.05
    æĦıçļĦ
    0.05
    {}_
    0.05
    åºĶå°Ĩ
    0.05
    Activations Density 0.016%

    No Known Activations