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. 162264
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    __.__
    -0.27
    ofire
    -0.27
    ipi
    -0.25
    éªĭ
    -0.25
    /legal
    -0.24
    ahi
    -0.24
    ayer
    -0.24
    oire
    -0.23
    icing
    -0.23
     sue
    -0.23
    POSITIVE LOGITS
    ç´§è¿«
    0.27
     obscured
    0.26
    zon
    0.26
     opaque
    0.24
    uated
    0.24
    éĿ¢çĽ®
    0.24
    folio
    0.24
     scope
    0.24
    enza
    0.23
     bulk
    0.23
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.