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. 15166
    Prev
    Next
    INDEX
    Explanations

    Technical documents

    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
     toc
    -0.30
     NSK
    -0.30
     tung
    -0.30
    ÑĤок
    -0.28
    æ¼ī
    -0.28
     plate
    -0.28
     plates
    -0.27
     sty
    -0.27
    æĪij说
    -0.26
    çıŀ
    -0.26
    POSITIVE LOGITS
    <hr
    0.28
    uan
    0.27
    (pe
    0.27
    otine
    0.26
    渴
    0.25
    pe
    0.25
    cla
    0.25
    cope
    0.25
    mor
    0.25
    è°ĭ
    0.25
    Activations Density 0.886%

    No Known Activations