© 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. 21864
    Prev
    Next
    INDEX
    Explanations

    medical and health institutions or services

    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
    anio
    -0.06
    asten
    -0.06
    оба
    -0.06
    aggio
    -0.06
    azon
    -0.06
    åĽ½è´¸
    -0.06
     STRING
    -0.06
    rott
    -0.06
    adeira
    -0.06
    STRING
    -0.06
    POSITIVE LOGITS
    -guard
    0.05
     guard
    0.05
     internal
    0.05
    æĭĵå±ķ
    0.05
    è¦ģçľĭ
    0.05
    èĩªçĶ±åº¦
    0.05
    conduct
    0.05
    ä¾ĿèµĸæĢ§
    0.05
    èĢĥ
    0.05
    alytics
    0.05
    Activations Density 0.008%

    No Known Activations