© 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. 16881
    Prev
    Next
    INDEX
    Explanations

    dates, combinations, colours, files, objects, providers, library, station, ratio

    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
    ysz
    -0.06
     Galer
    -0.05
    åľ¨ä¸ĸ
    -0.05
    ä¸įåIJĮçļĦæĺ¯
    -0.05
    æĹłçĸij
    -0.05
    inheit
    -0.05
    ëĵ¬
    -0.05
    मà¥į
    -0.05
    ä¹ĭä¸ĢçļĦ
    -0.05
     Norse
    -0.05
    POSITIVE LOGITS
    ä¸Ģåı¶
    0.06
    erra
    0.06
    olver
    0.06
    à¸Ńà¸ģà¸Īาà¸ģ
    0.06
    ç¾ļ
    0.06
     Tre
    0.05
    cente
    0.05
    wick
    0.05
    rell
    0.05
    ä¸Ĭä¸Ģ
    0.05
    Activations Density 0.006%

    No Known Activations