© 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. 17222
    Prev
    Next
    INDEX
    Explanations

    sistema program list

    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
    à¸Ļาà¸Ļ
    -0.08
    à¸Ļะ
    -0.08
    ë¥ł
    -0.08
    à¸Ļ
    -0.08
    ìľ¼ë¡ľëĬĶ
    -0.07
    rut
    -0.07
    åı£çļĦ
    -0.07
    koli
    -0.07
    à¸Ļะà¸Ħรัà¸ļ
    -0.07
    sWith
    -0.07
    POSITIVE LOGITS
    Ìģ
    0.06
    empre
    0.06
    impegno
    0.06
    o
    0.06
    о
    0.06
    ÌĢ
    0.06
    ãģĦãģĨ
    0.06
    ìĻĢ
    0.06
    ductory
    0.06
    ا
    0.06
    Activations Density 0.003%

    No Known Activations