© 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. 16622
    Prev
    Next
    INDEX
    Explanations

    date and time imports

    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
    Negative Logits
    ame
    -0.07
     mises
    -0.06
    ô
    -0.05
    dul
    -0.05
     fermo
    -0.05
    fall
    -0.05
    anton
    -0.05
    ä¹ĭ为
    -0.05
    anguage
    -0.05
    cel
    -0.05
    POSITIVE LOGITS
    st
    0.06
    æ¦ķ
    0.06
    ingang
    0.06
    веÑĢÑĪенно
    0.05
    ترÛĮÙĨ
    0.05
    ÑģÑĤи
    0.05
    å¦Ĥæ°´
    0.05
    æĮģ
    0.05
     inst
    0.05
    符
    0.05
    Activations Density 0.001%

    No Known Activations