© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21838
    Prev
    Next
    INDEX
    Explanations

    morbidity and mortality

    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
    estruct
    -0.06
    ihn
    -0.06
    нÑĮ
    -0.05
    าà¸Ļ
    -0.05
    çī¹å®ļ
    -0.05
    Ùĥرة
    -0.05
    .abs
    -0.05
    struk
    -0.05
    å°±æĽ´
    -0.05
    gom
    -0.05
    POSITIVE LOGITS
     and
    0.06
     et
    0.05
    otch
    0.05
     or
    0.05
    anden
    0.05
    åĴĮ
    0.05
    è´Ńä¹°åķĨåĵģ
    0.05
    биÑĤÑĮÑģÑı
    0.05
    ׼×Ŀ
    0.05
     и
    0.05
    Activations Density 0.065%

    No Known Activations