© 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. 18611
    Prev
    Next
    INDEX
    Explanations

    Java/Spring annotations autodoc

    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
    é½IJ家
    -0.05
    论
    -0.05
    åĿļæĮģ
    -0.05
    éĢŀ
    -0.05
    ufs
    -0.05
    Ù
    -0.05
     inscription
    -0.05
    egy
    -0.05
    thal
    -0.05
     ins
    -0.05
    POSITIVE LOGITS
     digestion
    0.06
    oja
    0.06
    ambilan
    0.06
    urna
    0.06
    кновен
    0.06
    оÑĢÑı
    0.06
    ç§Ģ丽
    0.06
    oha
    0.06
    gül
    0.06
    ,ep
    0.06
    Activations Density 0.002%

    No Known Activations