© 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. 20938
    Prev
    Next
    INDEX
    Explanations

    programming languages and technical terms

    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
    åĩºåĵģ
    -0.06
    ÙĦات
    -0.05
     natural
    -0.05
     dér
    -0.05
    é¢Ĥ
    -0.05
    éĢģå¾Ģ
    -0.05
    丽èİİ
    -0.05
    dest
    -0.05
     Wild
    -0.05
    ewise
    -0.05
    POSITIVE LOGITS
    ä¸Ĭæĺ¯
    0.06
    ìĥģìĿĢ
    0.06
    ici
    0.06
    æĢ§æĺ¯
    0.06
    åı²ä¸ĬæľĢ
    0.06
    *******
    0.05
    erras
    0.05
    æºĸ
    0.05
    ä¸İåħ±
    0.05
     pensi
    0.05
    Activations Density 0.184%

    No Known Activations