© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16866
    Prev
    Next
    INDEX
    Explanations

    special characters and spaces

    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
    Notice
    -0.06
     Notice
    -0.06
    éª
    -0.06
    aidu
    -0.06
    nach
    -0.06
    notice
    -0.06
    å½¢å¼ı
    -0.05
    %B
    -0.05
    ä¾
    -0.05
    çļĦå½¢å¼ı
    -0.05
    POSITIVE LOGITS
    kest
    0.07
     заÑīиÑĤиÑĤÑĮ
    0.06
    عÙĪ
    0.06
    impa
    0.06
    eltas
    0.06
    馴
    0.06
    uva
    0.06
     protect
    0.06
    ä¸ĩäºĭå¦ĤæĦı
    0.06
    lest
    0.06
    Activations Density 0.081%

    No Known Activations