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. 162252
    Prev
    Next
    INDEX
    Explanations

    verbal or manual actions

    np_max-act · gemini-2.0-flash
    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
    sembl
    -0.27
    çŃī级
    -0.27
    ç»Ŀ对
    -0.26
     softer
    -0.26
    åĽł
    -0.26
     pools
    -0.25
    ToJson
    -0.25
    æĽ´å¥½çļĦ
    -0.24
     coli
    -0.24
     differently
    -0.24
    POSITIVE LOGITS
     mounting
    0.31
     routing
    0.27
    ness
    0.27
    æłİ
    0.27
    amente
    0.26
    mente
    0.26
    izing
    0.26
    ly
    0.26
    Raised
    0.25
     routes
    0.25
    Activations Density 0.012%

    No Known Activations