© 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. 19555
    Prev
    Next
    INDEX
    Explanations

    # followed by *

    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
    иÑģÑĤеÑĢ
    -0.06
    à¸Ĭาà¸ķิ
    -0.06
    иÑħ
    -0.06
    urrent
    -0.06
    带åİ»
    -0.06
     trì
    -0.05
    äºĮæľ¬
    -0.05
    اط
    -0.05
    avn
    -0.05
    ivid
    -0.05
    POSITIVE LOGITS
    å¤ĦçIJĨæĸ¹å¼ı
    0.06
    Care
    0.05
    ossal
    0.05
    /tutorial
    0.05
    ä»Ģä¹ĪæĦıæĢĿ
    0.05
     Care
    0.05
    /releases
    0.05
    åħ´
    0.05
     frowned
    0.05
     care
    0.05
    Activations Density 0.018%

    No Known Activations