© 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. 17782
    Prev
    Next
    INDEX
    Explanations

    printf format specifiers

    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
    лека
    -0.06
     weakest
    -0.05
    rise
    -0.05
    ehör
    -0.05
     inform
    -0.05
    iphy
    -0.05
    讯
    -0.05
     наиболÑĮ
    -0.05
    åĵī
    -0.05
    oba
    -0.05
    POSITIVE LOGITS
    atap
    0.07
    ilan
    0.07
    ilh
    0.06
    åĪ°è¿Ļ
    0.06
    åľ¨ç»Ļ
    0.06
    ollo
    0.06
    åĪ°ä½łçļĦ
    0.06
    æĸĩç«łäºĨ
    0.06
    aut
    0.06
    åĪ°å¤©
    0.06
    Activations Density 0.003%

    No Known Activations