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. 15116
    Prev
    Next
    INDEX
    Explanations

    the

    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
     late
    -0.39
    æĻļæľŁ
    -0.34
    Later
    -0.32
    æ¯ı天
    -0.32
     later
    -0.32
    late
    -0.31
    Late
    -0.31
    later
    -0.30
     tar
    -0.30
     Late
    -0.29
    POSITIVE LOGITS
    è¦ĭ
    0.25
    .flink
    0.25
    abilidad
    0.25
    plets
    0.24
    ervo
    0.24
    Fizz
    0.24
    è¿ĩ
    0.24
     spur
    0.24
    igu
    0.24
    ugal
    0.24
    Activations Density 0.103%

    No Known Activations