© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19670
    Prev
    Next
    INDEX
    Explanations

    annually, once, naturally, first, normally

    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
     resulting
    -0.06
    eea
    -0.06
    anky
    -0.06
    èĢĮ论
    -0.05
    ä»Ģä¹Īæĺ¯
    -0.05
    æĺ¯ä¸į
    -0.05
    kker
    -0.05
    ìķŀ
    -0.05
    æĿ¥è®²
    -0.05
     nech
    -0.05
    POSITIVE LOGITS
    анÑĤи
    0.06
    ä»İ天
    0.06
    iful
    0.06
    atory
    0.05
     helpful
    0.05
    çĬ¶çļĦ
    0.05
    aikan
    0.05
     enough
    0.05
    EMP
    0.05
    äºĪ
    0.05
    Activations Density 0.084%

    No Known Activations