© 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. 19490
    Prev
    Next
    INDEX
    Explanations

    questions and exclamations

    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
    althy
    -0.06
    retch
    -0.06
    unge
    -0.06
    å¼ĢæĿ¥
    -0.06
    å§ĭ
    -0.06
     Figu
    -0.06
    èIJĮ
    -0.06
    ogen
    -0.05
    æ½
    -0.05
    è¿ĩä½İ
    -0.05
    POSITIVE LOGITS
    ÑĤиÑĤ
    0.06
    ça
    0.06
    errat
    0.06
    icultura
    0.05
     usually
    0.05
     guaranteed
    0.05
    èIJį
    0.05
     Willi
    0.05
    resolved
    0.05
     promises
    0.05
    Activations Density 0.003%

    No Known Activations