© 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
    2. Qwen3.5-4B
    3. 15-RES-MATRYOSHKA-65K
    4. 17301
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ÑıÑģ
    -0.06
    etween
    -0.06
    huis
    -0.06
    astery
    -0.05
    RY
    -0.05
    ytä
    -0.05
    ÙĪÙĨÙĩ
    -0.05
    .jsdelivr
    -0.05
    _house
    -0.05
    õi
    -0.05
    POSITIVE LOGITS
    åģļ好åĩĨå¤ĩ
    0.06
    ä¸įè¿ĩ
    0.06
    rej
    0.06
    åħī
    0.06
    ÑĦилÑĮ
    0.05
    åģļçļĦäºĭ
    0.05
    à¸Ķัà¸ļ
    0.05
     ê°ĢìĨį
    0.05
    rezz
    0.05
    æĸĩæĺİ
    0.05
    Activations Density 0.000%

    No Known Activations