© 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. 17585
    Prev
    Next
    INDEX
    Explanations

    if condition checks

    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
    ``
    -0.06
    geries
    -0.06
    ارة
    -0.06
     Gerr
    -0.06
    essel
    -0.06
    ator
    -0.06
    æĸĹ
    -0.06
    ner
    -0.06
    æĸ°åĮº
    -0.06
    ÙħØ´
    -0.06
    POSITIVE LOGITS
    èĬ¥
    0.05
     substitute
    0.05
    æĿ¥éĢīæĭ©
    0.05
    è¿Ļä¸į
    0.05
     successive
    0.05
    ranken
    0.05
    olini
    0.05
    Ã¤ÃŁ
    0.05
    该款
    0.05
     incoming
    0.05
    Activations Density 0.029%

    No Known Activations