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. 162108
    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
    æĺ¯æ¯Ķè¾ĥ
    -0.26
     saÄŁlam
    -0.25
    |i
    -0.25
    ipel
    -0.24
    rios
    -0.24
     unregister
    -0.23
    Spr
    -0.23
     Documents
    -0.23
     motive
    -0.23
    åİĭè¿«
    -0.23
    POSITIVE LOGITS
    çIJ¥
    0.29
    erver
    0.28
    çĿ¡
    0.26
    cplusplus
    0.25
    æ°ij
    0.24
     <",
    0.24
     landsc
    0.24
    wart
    0.24
    èįī
    0.24
    erving
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.