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. 162122
    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
    æİ¨ä»ĭ
    -0.26
     tri
    -0.26
     fused
    -0.25
    )o
    -0.24
    /apis
    -0.24
    .getConnection
    -0.24
     ims
    -0.24
    çīĽå¥¶
    -0.24
    mlink
    -0.24
     Bundy
    -0.24
    POSITIVE LOGITS
     resources
    0.26
    IRM
    0.26
     lenght
    0.24
    æ°ĶåĢĻ
    0.24
    /fast
    0.24
    åĹij
    0.24
    â¬ħ
    0.24
    åĿĢ
    0.24
    IÃĬ
    0.23
    建
    0.23
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.