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. 23-TRANSCODER-HP
    4. 162228
    Prev
    Next
    INDEX
    Explanations

    Formal documents

    np_max-act · 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
    æ¼ī
    -0.27
    ws
    -0.27
    ä¸įåIJ«
    -0.26
    ä¸įåħ·å¤ĩ
    -0.25
    ап
    -0.25
     Symphony
    -0.24
    apel
    -0.24
    ãģªãĤĤãģ®
    -0.24
    contain
    -0.23
    çIJĨæĢ§
    -0.23
    POSITIVE LOGITS
     hereby
    0.31
    inoa
    0.29
    aida
    0.27
    redi
    0.26
    å§Ķ
    0.25
    èĸ¯
    0.25
    ocks
    0.25
    çļĦ身份
    0.24
    rowning
    0.24
    ariate
    0.24
    Activations Density 0.010%

    No Known Activations