© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19008
    Prev
    Next
    INDEX
    Explanations

    python packages paths

    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·®
    -0.06
    æł¹æľ¬ä¸Ĭ
    -0.06
    åĬĽåĴĮ
    -0.05
    大çģ«
    -0.05
    渡
    -0.05
    éŀ
    -0.05
    使å¾Ĺ
    -0.05
    enburg
    -0.05
    æ±Ĥæĺ¯
    -0.05
    ä¸ĭæ°´
    -0.05
    POSITIVE LOGITS
     nhau
    0.06
    osed
    0.06
    à¸Ĺà¸Ńà¸Ķ
    0.06
    åįİåºŃ
    0.06
    messe
    0.06
     hamb
    0.06
    Õ¸ÖĢ
    0.06
    verse
    0.05
    assis
    0.05
    ä¸įåĪ°äºĨ
    0.05
    Activations Density 0.003%

    No Known Activations