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. 162097
    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
    åħ¶
    -0.26
     endregion
    -0.26
     Prelude
    -0.25
    æīĢè°ĵ
    -0.25
    è¿ĺæĺ¯
    -0.25
    itemap
    -0.24
     Claw
    -0.24
     Naomi
    -0.24
    å¿ĥ
    -0.24
    éĶ»éĢł
    -0.24
    POSITIVE LOGITS
     actively
    0.27
     thr
    0.26
     mass
    0.26
     disciplined
    0.26
     unw
    0.25
     personally
    0.25
     college
    0.25
     five
    0.25
     quadr
    0.25
     fruit
    0.25
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.