© 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. 22423
    Prev
    Next
    INDEX
    Explanations

    patients with conditions

    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
     mai
    -0.06
    oka
    -0.06
    åĴĮä¸Ģ
    -0.05
     rail
    -0.05
    oin
    -0.05
     nunca
    -0.05
    Pu
    -0.05
    èĮ¹
    -0.05
     rein
    -0.05
     Kling
    -0.05
    POSITIVE LOGITS
    à¸Ĺัà¸Ļ
    0.06
    éĤ£åĦ¿
    0.06
    toffe
    0.06
    并åIJij
    0.05
    æĸŁ
    0.05
    imd
    0.05
    bastian
    0.05
    ÙħØŃ
    0.05
    çİ°åľº
    0.05
    åı©
    0.05
    Activations Density 0.013%

    No Known Activations