© 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. 20821
    Prev
    Next
    INDEX
    Explanations

    medication use or adherence

    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
    代ãģ®
    -0.06
    åģļ大åģļ强
    -0.06
    产ä¸ļåıijå±ķçļĦ
    -0.06
     disastr
    -0.06
    æĪijåIJĥ
    -0.06
    Ùĩ
    -0.06
    anzeigen
    -0.06
     hụt
    -0.06
     arqu
    -0.06
    并ç»ĵåIJĪ
    -0.06
    POSITIVE LOGITS
    res
    0.06
    ä¸īéģĵ
    0.05
    elson
    0.05
     Stem
    0.05
    ç´¢
    0.05
    æ»ĭ
    0.05
    erset
    0.05
    oren
    0.05
    ↵
    0.05
    à¼
    0.05
    Activations Density 0.006%

    No Known Activations