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. 162700
    Prev
    Next
    INDEX
    Explanations

    Scraped website text

    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
    æŁ¥çľĭ详æĥħ
    -0.29
    åİĺ
    -0.29
    illage
    -0.27
    amarin
    -0.26
    æĪĸå¤ļæĪĸå°ij
    -0.25
    Thin
    -0.24
     pager
    -0.24
    ippet
    -0.24
    广
    -0.23
     analysis
    -0.23
    POSITIVE LOGITS
    ä¸ĭæĿ¥
    0.27
    orpion
    0.26
    çĦī
    0.25
    uids
    0.24
     seks
    0.24
    ôt
    0.24
    é͝
    0.23
    ä½ı宿
    0.23
     prima
    0.23
    ħ§
    0.23
    Activations Density 0.003%

    No Known Activations