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. 162714
    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
    ä¸Ģ份
    -0.32
     ca
    -0.30
     '
    -0.29
     beating
    -0.29
     '↵
    -0.27
     n
    -0.26
     p
    -0.25
    ---
    -0.25
     ‘
    -0.25
    ÑĤе
    -0.25
    POSITIVE LOGITS
     <![
    0.28
    /entities
    0.26
    sterdam
    0.26
    æijĺç¼ĸ
    0.26
    antha
    0.26
    igrams
    0.25
    ographers
    0.25
    ceptors
    0.25
    eldon
    0.25
    å°Ħæīĭ
    0.25
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.