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. 15163
    Prev
    Next
    INDEX
    Explanations

    Programming code

    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
     bed
    -0.31
    -be
    -0.29
    åºĬ
    -0.26
    -bed
    -0.26
     cover
    -0.26
    bage
    -0.26
     plots
    -0.25
     Bed
    -0.25
     forb
    -0.25
     beat
    -0.24
    POSITIVE LOGITS
    论æĸĩ
    0.31
    ĽĦ
    0.28
    人éĹ´
    0.28
    uma
    0.27
    çļĦæĦŁè§ī
    0.27
    èĺħ
    0.25
    amer
    0.25
    papers
    0.25
    享æľī
    0.25
    umes
    0.24
    Activations Density 0.003%

    No Known Activations