© 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. 17828
    Prev
    Next
    INDEX
    Explanations

    parents and family relationships

    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
    åįĥæĸ¹
    -0.06
    addock
    -0.06
    ç»ĵ
    -0.06
    ож
    -0.06
     zd
    -0.06
     descar
    -0.06
    ستاÙĨ
    -0.06
    à¹Ĥà¸Ķยà¸ķรà¸ĩ
    -0.06
     liga
    -0.06
     vested
    -0.06
    POSITIVE LOGITS
    æ¢Ń
    0.06
    annt
    0.05
    ç§ijåѦçļĦ
    0.05
    ä¸ĩä¸Ģ
    0.05
    åħ¬åı¸äºİ
    0.05
    temp
    0.05
    asma
    0.05
    es
    0.05
     pur
    0.05
    æĴ¤
    0.05
    Activations Density 0.028%

    No Known Activations