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. 15115
    Prev
    Next
    INDEX
    Explanations

    yeast genes

    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
    ngine
    -0.28
    é²ij
    -0.26
    Engine
    -0.26
     hứng
    -0.25
     animal
    -0.25
    pond
    -0.25
    engine
    -0.25
    çĶŁçī©
    -0.24
    CHED
    -0.24
    .ai
    -0.24
    POSITIVE LOGITS
    å¯Ħ
    0.27
    æijĩ
    0.26
    è¹´
    0.26
    æĹłäºº
    0.26
    txt
    0.25
    Äı
    0.25
    ä¸Ńå°ı
    0.24
    èººåľ¨
    0.24
    ä»İå°ı
    0.24
    èĩªå®¶
    0.24
    Activations Density 0.004%

    No Known Activations