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. 15242
    Prev
    Next
    INDEX
    Explanations

    pixel

    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
    urge
    -0.25
    âĬĩ
    -0.25
     senior
    -0.25
    çĿ£å¯¼
    -0.25
    æ»ļçIJĥ
    -0.24
    è½®
    -0.24
     system
    -0.24
    bound
    -0.24
    ulse
    -0.24
     Monitoring
    -0.24
    POSITIVE LOGITS
    è§Ħ模
    0.30
    entes
    0.29
    åį°è±¡
    0.29
    åĮĸè¿Ľç¨ĭ
    0.27
    phia
    0.27
    ensity
    0.26
     bö
    0.26
    .Program
    0.26
    Strength
    0.25
    ights
    0.25
    Activations Density 0.895%

    No Known Activations