© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19578
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    .bi
    -0.06
    beck
    -0.05
    astos
    -0.05
    dw
    -0.05
     ìķĮ볤ì¡Įëĭ¤
    -0.05
     tá»Ŀ
    -0.05
    구ìļĶ
    -0.05
    åªĽ
    -0.05
    kas
    -0.05
     bureaucr
    -0.05
    POSITIVE LOGITS
     ev
    0.06
    ä¼ļåIJĮ
    0.06
    åįı
    0.06
    éķĩ
    0.05
    egy
    0.05
    çī¹
    0.05
    ìĺ¬
    0.05
     dé
    0.05
     zusammen
    0.05
    æĹģè¾¹çļĦ
    0.05
    Activations Density 0.001%

    No Known Activations