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. 162230
    Prev
    Next
    INDEX
    Explanations

    news articles

    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
    .hu
    -0.28
     available
    -0.26
    leo
    -0.25
    robat
    -0.25
    stral
    -0.25
    顺åĪ©
    -0.24
     disponible
    -0.24
     swear
    -0.24
    çŁĽçĽ¾
    -0.24
    人æŃ»äº¡
    -0.24
    POSITIVE LOGITS
    èľĪ
    0.29
     ADV
    0.28
    undi
    0.27
    ev
    0.27
     reform
    0.26
     sodom
    0.26
     Adv
    0.26
     Chart
    0.25
    éĵº
    0.25
    essor
    0.25
    Activations Density 0.005%

    No Known Activations