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. 15298
    Prev
    Next
    INDEX
    Explanations

    gent

    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
    丫
    -0.32
    ish
    -0.30
     dos
    -0.27
    åij½åIJį
    -0.27
    lop
    -0.26
     Bald
    -0.26
    ÃŃd
    -0.26
    lea
    -0.26
    ond
    -0.25
    vido
    -0.25
    POSITIVE LOGITS
    ree
    0.27
    ents
    0.26
    rique
    0.26
    /icons
    0.25
    ente
    0.25
     trừ
    0.25
     Weiner
    0.25
    acles
    0.25
     IonicPage
    0.24
    å¥İ
    0.24
    Activations Density 0.101%

    No Known Activations