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. 162260
    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
     pris
    -0.26
    VIC
    -0.26
    rice
    -0.25
    .jsp
    -0.25
    intree
    -0.25
    icz
    -0.24
    çĪ±ä½ł
    -0.24
    pisa
    -0.24
     uncertain
    -0.23
    _alignment
    -0.23
    POSITIVE LOGITS
    å°ij
    0.28
    åıijæĮ¥
    0.27
    åħijçݰ
    0.27
    æ¯Ľ
    0.26
    -ln
    0.25
    æİĢ
    0.24
    æİĺ
    0.24
    輸
    0.24
    rogram
    0.24
    éħįç½®
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.