© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20331
    Prev
    Next
    INDEX
    Explanations

    independence

    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
    æĸ¹å¼ıæĿ¥
    -0.07
    ä¸İ家人
    -0.07
    æĸ¹æ³ķæĿ¥
    -0.06
    olÃŃ
    -0.06
    æĸ¹å¼ı使çĶ¨
    -0.06
     Comunic
    -0.06
    idup
    -0.06
    ìĿ¼ë¡ľ
    -0.06
    alais
    -0.06
    æ²ŁæĿij
    -0.06
    POSITIVE LOGITS
    çĭ¬ç«ĭ
    0.08
    çį¨ç«ĭ
    0.07
     independently
    0.06
     ëıħ립
    0.06
     independent
    0.06
    çĭ¬ç«ĭçļĦ
    0.06
    çĭ¬ç«ĭæĢ§
    0.06
     independence
    0.06
    uj
    0.06
    çĭ¬è§Ĵ
    0.06
    Activations Density 0.004%

    No Known Activations