© 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. 21780
    Prev
    Next
    INDEX
    Explanations

    mathematical operations or counting

    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
    лÑİ
    -0.05
    ç®Ģ称
    -0.05
    ÙĦس
    -0.05
    人æ°ijå¸ģ
    -0.05
    szcz
    -0.05
    oba
    -0.05
     viên
    -0.05
    簡稱
    -0.05
    个åŃIJ
    -0.05
    azionali
    -0.05
    POSITIVE LOGITS
    bach
    0.07
    åIJĴ
    0.06
    год
    0.06
    è¿Ń
    0.05
    ç¾ļ
    0.05
     اتÙĩاÙħ
    0.05
    OH
    0.05
    笼
    0.05
    pg
    0.05
    èĩªå·±çļĦè¡Į为
    0.05
    Activations Density 0.012%

    No Known Activations