© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18421
    Prev
    Next
    INDEX
    Explanations

    New Year's Day/Eve/Honours

    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
    ä¸įåĪ°çļĦ
    -0.07
    åĨµ
    -0.06
    ä¸ĬéŨ
    -0.06
    abouts
    -0.06
    çļĦä»Ĭ天
    -0.06
    althy
    -0.06
    ä¸įèµ·æĿ¥
    -0.06
    شد
    -0.06
    adays
    -0.06
    noon
    -0.06
    POSITIVE LOGITS
    å¾ĮãĤĤ
    0.05
    urn
    0.05
    reu
    0.05
    емÑĥ
    0.05
     survive
    0.05
    and
    0.05
     пÑĢазд
    0.05
    à¸Ĭà¸Ļ
    0.05
    fried
    0.05
     popular
    0.05
    Activations Density 0.037%

    No Known Activations