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. 15184
    Prev
    Next
    INDEX
    Explanations

    amy

    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
    anted
    -0.29
     cold
    -0.27
    ib
    -0.27
    åĨ·
    -0.26
     cross
    -0.26
    озв
    -0.25
     Placement
    -0.24
    æ±Ĭ
    -0.24
     patent
    -0.24
     brushed
    -0.24
    POSITIVE LOGITS
    壮
    0.28
    wil
    0.27
    uter
    0.26
    kir
    0.26
    anel
    0.25
    éħ
    0.25
    æĹħ
    0.25
    壯
    0.24
    umer
    0.24
     Randy
    0.24
    Activations Density 0.003%

    No Known Activations