© 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. 21326
    Prev
    Next
    INDEX
    Explanations

    prime factors and products

    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
    åĬ£
    -0.07
    -0.06
    ãĤīãģĦ
    -0.05
     due
    -0.05
    æķ´çIJĨ
    -0.05
     re
    -0.05
    ès
    -0.05
     punch
    -0.05
     graz
    -0.05
    uvat
    -0.05
    POSITIVE LOGITS
    isma
    0.07
     distanci
    0.07
    èĢĮä¸Ķè¦ģ
    0.07
    æ¼ł
    0.07
    aliste
    0.06
    éļĶèĨľ
    0.06
     Abstand
    0.06
     musim
    0.06
     khuyết
    0.06
    æݧèĤ¡éĽĨåĽ¢
    0.06
    Activations Density 0.003%

    No Known Activations