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. 163251
    Prev
    Next
    INDEX
    Explanations

    Qualifying adverbs

    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
    atis
    -0.28
     a
    -0.27
    æµģåIJij
    -0.26
    â̦↵
    -0.26
    ç±
    -0.26
    ä¹Ĥ
    -0.26
    è¿Ļéĥ¨åĪĨ
    -0.26
    çķĻç»Ļ
    -0.25
     Âł
    -0.25
    ä»Ģä¹Īéĥ½ä¸į
    -0.25
    POSITIVE LOGITS
    -Mart
    0.27
    ény
    0.27
     huge
    0.27
     drastic
    0.26
    udas
    0.26
     massive
    0.26
    æµĵéĥģ
    0.25
    .lv
    0.25
     tremendous
    0.25
    æijĩ头
    0.25
    Activations Density 0.008%

    No Known Activations