© 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. 22169
    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
    оÑĩи
    -0.06
     Lunes
    -0.06
    à¸ķà¹īม
    -0.05
    iop
    -0.05
     bersangkutan
    -0.05
    -worker
    -0.05
    被éĢ¼
    -0.05
    stice
    -0.05
    emuk
    -0.05
    交æīĢ
    -0.05
    POSITIVE LOGITS
    ä¸įæĪIJ
    0.06
     pres
    0.05
    ett
    0.05
    aken
    0.05
    -addons
    0.05
    ral
    0.05
    ص
    0.05
    ений
    0.05
     ken
    0.05
    ï¼ļ**
    0.05
    Activations Density 0.000%

    No Known Activations