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. 163665
    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
    iless
    -0.26
     **/↵↵
    -0.25
    åĸij
    -0.25
    zin
    -0.24
    lfw
    -0.23
    çݰæľī
    -0.23
     **/↵
    -0.23
    ",-
    -0.23
    chip
    -0.23
    _faces
    -0.23
    POSITIVE LOGITS
    indsight
    0.29
    stances
    0.25
    è¿ĻäºĽéĹ®é¢ĺ
    0.25
    带
    0.23
    帶
    0.23
     Decimal
    0.23
    éĹªç͵
    0.23
     Bod
    0.23
    ç±»åŀĭçļĦ
    0.23
     Spatial
    0.22
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.