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. 30-TRANSCODER-HP
    4. 15139
    Prev
    Next
    INDEX
    Explanations

    global

    np_max-act-logits · 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
    acos
    -0.28
     Ud
    -0.28
     watchers
    -0.26
    æī©
    -0.26
    afa
    -0.25
     Com
    -0.24
     coma
    -0.24
     Co
    -0.23
    entic
    -0.23
     true
    -0.23
    POSITIVE LOGITS
    èĩªåıij
    0.28
    Verse
    0.27
     dru
    0.26
    询
    0.26
    éĺĨ
    0.25
    itat
    0.25
    moduleId
    0.25
    èĨĽ
    0.25
     manoe
    0.25
     tit
    0.25
    Activations Density 0.118%

    No Known Activations