© 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. 17882
    Prev
    Next
    INDEX
    Explanations

    defining code syntax or structure

    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
    ä¾ĭ
    -0.06
     esempio
    -0.05
     example
    -0.05
    Dire
    -0.05
    /example
    -0.05
    instead
    -0.05
     пÑĢаве
    -0.05
    .example
    -0.05
     misalnya
    -0.05
     loro
    -0.04
    POSITIVE LOGITS
    awal
    0.06
     desi
    0.06
    pai
    0.06
     pasto
    0.06
    Ú©ÛĮ
    0.06
     skut
    0.06
    ulut
    0.06
    ç»Ī
    0.06
    rades
    0.06
    æĺ±
    0.06
    Activations Density 0.001%

    No Known Activations