© 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. 17656
    Prev
    Next
    INDEX
    Explanations

    equations with symbols

    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
    /
    -0.06
    د
    -0.05
     (
    -0.05
    -case
    -0.05
     Ñĥ
    -0.05
    cel
    -0.05
     [
    -0.05
     consum
    -0.04
     cont
    -0.04
    ogh
    -0.04
    POSITIVE LOGITS
    迪æĸ¯
    0.07
     Uncategorized
    0.07
     drauf
    0.06
    ä¾Ŀæ³ķ追究责任
    0.06
    ä¼łç»Łäº§ä¸ļ
    0.06
    åıĺæĽ´è®°å½ķ
    0.06
     DiÄŁer
    0.06
    ãģ«ãģĤãģŁ
    0.06
    rolet
    0.06
    iteurs
    0.06
    Activations Density 0.001%

    No Known Activations