Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 30-TRANSCODER-HP
    4. 15191
    Prev
    Next
    INDEX
    Explanations

    mixed code/documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    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
     separately
    -0.76
     independently
    -0.71
     manually
    -0.67
     peacefully
    -0.65
     individually
    -0.64
     orally
    -0.64
     verbally
    -0.60
     efficiently
    -0.60
     sequentially
    -0.59
     dynamically
    -0.59
    POSITIVE LOGITS
    éļIJèĹı
    0.29
    rys
    0.26
    ä¸įçķĻ
    0.25
    çϾå§ĵ
    0.25
    管çIJĨ模å¼ı
    0.25
    åľ»
    0.25
    æľĢåIJİä¸Ģ
    0.25
    åŃĺåľ¨äºİ
    0.24
    è¶ĭåIJij
    0.24
    æĹ¶ä»£ä¸ŃåĽ½
    0.24
    Activations Density 0.907%

    No Known Activations