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. 15157
    Prev
    Next
    INDEX
    Explanations

    get

    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
    rades
    -0.27
    æĬĬæīĭ
    -0.26
    anean
    -0.26
    ä½ı
    -0.25
    ä½ıäºĨ
    -0.25
     growth
    -0.25
     living
    -0.25
    'il
    -0.24
    addon
    -0.24
    esan
    -0.24
    POSITIVE LOGITS
    ä¸ĭæĿ¥
    0.31
    大éĻĨ
    0.29
    umped
    0.28
    大éϏ
    0.27
    InSection
    0.27
    mes
    0.26
    亵
    0.26
    _mes
    0.26
     Mes
    0.25
    cloth
    0.25
    Activations Density 0.115%

    No Known Activations