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. 15129
    Prev
    Next
    INDEX
    Explanations

    Temples and cities

    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
    åĽłä¸ºæĪij们
    -0.25
    ายà¸Ļ
    -0.25
    DOWN
    -0.25
    icator
    -0.24
    çĬ¶
    -0.24
    ä½IJ
    -0.24
     eros
    -0.23
    é¢Ĺ
    -0.23
    eros
    -0.23
     Damascus
    -0.23
    POSITIVE LOGITS
    å¡Ķ
    0.37
     tower
    0.31
    çĮ´
    0.30
     wall
    0.28
    寺
    0.27
    æ³ĵ
    0.27
    /site
    0.27
    wall
    0.26
    walls
    0.26
    榱
    0.26
    Activations Density 0.886%

    No Known Activations