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. 15228
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical texts

    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
    igator
    -0.27
    éı¡
    -0.27
    å¯ĨéĽĨ
    -0.26
    (cs
    -0.26
    éķľ
    -0.26
     resignation
    -0.26
    åĮ»åѦ
    -0.26
    é¡¿
    -0.25
    TERN
    -0.25
    ron
    -0.24
    POSITIVE LOGITS
     slee
    0.29
    æĿĢäºĨ
    0.28
     unfavor
    0.27
    .FILL
    0.27
     obsc
    0.25
    çľĭäºĨçľĭ
    0.25
    .fill
    0.25
    chie
    0.25
    çݺ
    0.25
     Stanley
    0.24
    Activations Density 0.885%

    No Known Activations