© 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. 19536
    Prev
    Next
    INDEX
    Explanations

    aka, followed by names

    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
    cha
    -0.05
    Ł
    -0.05
    anton
    -0.05
    sze
    -0.05
    ÙĨب
    -0.05
    aan
    -0.05
    aos
    -0.05
    ambut
    -0.05
    ÑĩÑĸ
    -0.04
    CHA
    -0.04
    POSITIVE LOGITS
    cheid
    0.06
    .MaxValue
    0.06
    ä¹Łæĺ¯æľĢ
    0.06
    åĮ¹
    0.06
    abancı
    0.06
    à¸Ĥวัà¸į
    0.06
    rodomést
    0.06
    ulous
    0.06
     indeb
    0.06
    å¤©åĽ½
    0.06
    Activations Density 0.035%

    No Known Activations