© 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. 17665
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and code snippets

    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
    klas
    -0.06
    天éŃĶ
    -0.06
    kst
    -0.06
    ä¸įåĢ¼
    -0.06
    大éĢļ
    -0.05
    {o
    -0.05
    producer
    -0.05
    *\
    -0.05
    ñas
    -0.05
    æĸ¯é¡¿
    -0.05
    POSITIVE LOGITS
    交
    0.06
    olut
    0.06
    交çļĦ
    0.06
    æİ·
    0.05
    .ByteArray
    0.05
    rechtliche
    0.05
     mor
    0.05
     incluidos
    0.05
     incluida
    0.05
    岸
    0.05
    Activations Density 0.023%

    No Known Activations