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. 163247
    Prev
    Next
    INDEX
    Explanations

    all

    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
    äºĶå®ĺ
    -0.26
     democr
    -0.26
     orbital
    -0.25
     fine
    -0.25
     Knight
    -0.25
     knight
    -0.24
     mỹ
    -0.24
     different
    -0.24
     finance
    -0.24
    thon
    -0.24
    POSITIVE LOGITS
    è¿Ķ
    0.27
    gó
    0.26
    äu
    0.26
    icut
    0.25
    uality
    0.25
    ervoir
    0.25
     __(
    0.24
    å®ŀç͍æĢ§
    0.24
    ifix
    0.24
     "\""
    0.24
    Activations Density 0.015%

    No Known Activations