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. 15117
    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
    emente
    -0.29
    ocks
    -0.26
    çϽ天
    -0.24
    eken
    -0.24
     ffm
    -0.24
    形象
    -0.24
    loquent
    -0.24
    ement
    -0.23
    urar
    -0.23
     Wikimedia
    -0.23
    POSITIVE LOGITS
    acje
    0.27
    ä¸Ģè´¯
    0.26
    为æŃ¢
    0.24
    yar
    0.24
     acab
    0.23
    ones
    0.23
    opper
    0.23
    "She
    0.23
    rig
    0.23
     j
    0.23
    Activations Density 0.103%

    No Known Activations

    This feature has no known activations.