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. 15093
    Prev
    Next
    INDEX
    Explanations

    hurricane

    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
     arc
    -0.29
     meaning
    -0.27
    impl
    -0.25
    Arc
    -0.25
     terra
    -0.25
     stat
    -0.25
     depos
    -0.25
     do
    -0.25
    yr
    -0.25
     presum
    -0.25
    POSITIVE LOGITS
    modelo
    0.30
    模åŀĭ
    0.29
    æĺ¯ä¸Ģå®¶
    0.28
    emodel
    0.26
    ä½ľä¸ļ
    0.26
     Modelo
    0.25
    anken
    0.24
     modelos
    0.24
     Wanted
    0.24
     errorCode
    0.24
    Activations Density 0.007%

    No Known Activations