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. 15109
    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
    Passwords
    -0.26
    rics
    -0.26
    yards
    -0.25
    elmet
    -0.25
    SES
    -0.25
    çĶij
    -0.24
     erb
    -0.24
    çĸ¼
    -0.24
     priced
    -0.23
    çİĩ为
    -0.23
    POSITIVE LOGITS
     feeding
    0.28
    lements
    0.28
    åĪ·
    0.27
    ersh
    0.25
     accumulation
    0.25
    ä¼ĺåĬ¿
    0.24
    ENTION
    0.24
     living
    0.24
    åĩĿ
    0.24
     shock
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.