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. 162210
    Prev
    Next
    INDEX
    Explanations

    commodities/goods

    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
    azel
    -0.26
     hypothetical
    -0.26
    ronym
    -0.26
    设计çIJĨ念
    -0.26
    emon
    -0.26
    ç»ıå¼Ģ
    -0.25
    afa
    -0.25
    aus
    -0.25
     ìŀħ
    -0.24
    çļĦ设计
    -0.23
    POSITIVE LOGITS
    lems
    0.29
    åıĬ
    0.28
    è¿ĩ
    0.26
     revenues
    0.25
    港
    0.25
    ères
    0.24
    cepts
    0.24
    зÑĥ
    0.24
    è¾ĵéĢģ
    0.24
    交
    0.24
    Activations Density 0.008%

    No Known Activations