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. 23-TRANSCODER-HP
    4. 162696
    Prev
    Next
    INDEX
    Explanations

    Text snippets

    np_max-act · 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
    kus
    -0.25
    ections
    -0.24
     Busy
    -0.22
    çĭ¬ä¸Ģ
    -0.22
    åľ¨åIJĮä¸Ģ
    -0.22
     comparatively
    -0.21
     bbc
    -0.21
     minor
    -0.21
     correct
    -0.21
     Scho
    -0.21
    POSITIVE LOGITS
    andy
    0.25
    æĦı大
    0.25
    orphism
    0.23
    ially
    0.23
    ierten
    0.23
    sembled
    0.23
    sy
    0.23
    attice
    0.22
    ç»Ŀ对
    0.22
    ðĿIJ¾
    0.22
    Activations Density 0.387%

    No Known Activations