© 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. 18130
    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
    ç¥ŀ
    -0.06
    ((((
    -0.06
    es
    -0.06
    ç§ijæĸ¯
    -0.06
    cour
    -0.05
    çĸ¯äºĨ
    -0.05
    æĸ¹å¼ı
    -0.05
    thood
    -0.05
    çī©
    -0.05
    глÑıд
    -0.05
    POSITIVE LOGITS
    æľįçļĦ
    0.06
    uit
    0.06
    ollen
    0.06
    宽çļĦ
    0.06
     gerne
    0.05
    uits
    0.05
    æĹłåīį
    0.05
    ষণ
    0.05
    ossen
    0.05
     orient
    0.05
    Activations Density 0.000%

    No Known Activations