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. 162118
    Prev
    Next
    INDEX
    Explanations

    scientific/technical subject matter

    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
    ä¸İæŃ¤
    -0.28
    rength
    -0.26
    hang
    -0.26
    éģĴ
    -0.26
    pal
    -0.24
    åı¦ä¸Ģ
    -0.24
    è°ij
    -0.24
    okes
    -0.24
    dfs
    -0.24
    leet
    -0.23
    POSITIVE LOGITS
     Dil
    0.29
    éĴĿ
    0.26
    /www
    0.25
    åŁºäºİ
    0.24
    è¿Ļæĺ¯æĪij
    0.24
     dil
    0.23
    ragon
    0.23
     due
    0.23
    icum
    0.23
    çºł
    0.23
    Activations Density 0.004%

    No Known Activations