© 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. 22087
    Prev
    Next
    INDEX
    Explanations

    authors or contributors

    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
    æĸ°åŀĭçļĦ
    -0.06
    èķī
    -0.06
     guna
    -0.05
    缮çļĦæĺ¯
    -0.05
     duplic
    -0.05
    ļ
    -0.05
    apesh
    -0.05
    oule
    -0.05
    两éģĵ
    -0.05
     br
    -0.05
    POSITIVE LOGITS
     subsequent
    0.07
    inks
    0.06
    åIJİç»Ń
    0.06
     Contributors
    0.06
     countless
    0.06
    彦
    0.06
     lifelong
    0.06
    ä¸įæĸŃå®ĮåĸĦ
    0.06
    æĹłæķ°ä¸ª
    0.06
    ä¾Ľ
    0.05
    Activations Density 0.002%

    No Known Activations