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. 15090
    Prev
    Next
    INDEX
    Explanations

    code and technical content

    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
     Interr
    -0.27
    ridge
    -0.27
    oland
    -0.26
    utr
    -0.25
    ÑĦеÑģÑģ
    -0.25
    wend
    -0.25
    agnitude
    -0.24
    çŁ¾
    -0.24
    bil
    -0.24
    amentals
    -0.24
    POSITIVE LOGITS
     prime
    0.27
    icle
    0.27
     subs
    0.25
    leh
    0.24
     prec
    0.24
     ///<
    0.24
    湿
    0.24
    avian
    0.24
    ä¾ĭè¡Į
    0.23
     spins
    0.23
    Activations Density 0.103%

    No Known Activations