© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19408
    Prev
    Next
    INDEX
    Explanations

    vomiting and related medical 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
    Not in Any Lists

    No Comments

    Negative Logits
     Ñģв
    -0.05
    æĺİ天
    -0.05
    onan
    -0.05
    semb
    -0.05
    æ°ij
    -0.05
     fug
    -0.05
     inferior
    -0.05
    lung
    -0.05
    ungs
    -0.05
    nea
    -0.05
    POSITIVE LOGITS
    .clf
    0.07
    å¾Ī好å¥ĩ
    0.07
    pite
    0.07
     Hogy
    0.06
    à¸Ľà¸£à¸²à¸ģาร
    0.06
    达峰
    0.06
    á»ijc
    0.06
    çݰ代åĮĸ建设
    0.06
    æ¥Ń主
    0.06
    иÑĤелÑĮÑģÑĤво
    0.06
    Activations Density 0.001%

    No Known Activations