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. 162172
    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
    æ¥Ķ
    -0.29
    ress
    -0.27
    ter
    -0.26
     mol
    -0.25
     at
    -0.25
    itative
    -0.25
    æĪijå¸ĮæľĽ
    -0.25
    uest
    -0.24
    ление
    -0.24
    oo
    -0.24
    POSITIVE LOGITS
    éĤĽ
    0.30
    AdapterFactory
    0.29
    .AF
    0.28
    adem
    0.26
    -directory
    0.26
    зон
    0.25
    ilage
    0.25
     subsidi
    0.25
    storybook
    0.25
    ondon
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.