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. 162709
    Prev
    Next
    INDEX
    Explanations

    danger and violence

    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
     Quinn
    -0.30
    ç¼µ
    -0.25
    bilt
    -0.25
    تاب
    -0.24
    iom
    -0.24
    æ»Ĺ
    -0.24
     abi
    -0.23
    roman
    -0.23
    ernal
    -0.23
    ernity
    -0.23
    POSITIVE LOGITS
    ä¼´éļı
    0.29
    åĿĽ
    0.28
     poisoned
    0.28
    çģ«çĥ§
    0.27
    èĩ´
    0.27
     sulph
    0.27
     anv
    0.27
    å¨ģèĥģ
    0.26
    éħĴç²¾
    0.26
    çł·
    0.26
    Activations Density 0.009%

    No Known Activations