© 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. 22608
    Prev
    Next
    INDEX
    Explanations

    .Field or .name access

    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
    ä¸Ģå®ļ
    -0.06
    minimum
    -0.06
    tec
    -0.05
    wer
    -0.05
    new
    -0.05
    bove
    -0.05
    ç»´
    -0.05
    >
    -0.05
     Minimum
    -0.05
    ä¿Ŀåį«æĪĺ
    -0.05
    POSITIVE LOGITS
    åIJijåİŁåijĬ
    0.06
    à¸ķรà¸ĩà¸ģัà¸ļ
    0.06
     sát
    0.06
    raub
    0.06
    tima
    0.06
    åIJĪåIJĮæŶ
    0.06
    æľĿçĿĢ
    0.06
    é¡·åĪ»
    0.05
    åĪ»
    0.05
    aat
    0.05
    Activations Density 0.026%

    No Known Activations