© 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. 19712
    Prev
    Next
    INDEX
    Explanations

    list items separated by 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
    æ
    -0.06
    org
    -0.05
    éķ¿æķĪ
    -0.05
    embed
    -0.05
    绣ä¸ĢæĢĿæĥ³
    -0.05
    ç»Ī究
    -0.05
    å©Ĩ
    -0.05
    ÙĦÙĤ
    -0.05
    order
    -0.04
    halb
    -0.04
    POSITIVE LOGITS
    andia
    0.07
    aeda
    0.07
    teau
    0.06
    .micro
    0.06
     either
    0.06
    yam
    0.06
    iserie
    0.06
    colo
    0.06
    vola
    0.06
    ândia
    0.06
    Activations Density 0.003%

    No Known Activations