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. 15094
    Prev
    Next
    INDEX
    Explanations

    with

    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
    .configure
    -0.28
    ged
    -0.25
    ä¸įåıĬ
    -0.25
    orate
    -0.25
    instanc
    -0.24
    PEC
    -0.24
    owed
    -0.24
    olah
    -0.24
    tip
    -0.23
    eneg
    -0.23
    POSITIVE LOGITS
    åŃĺ
    0.29
    ynet
    0.26
    veyor
    0.26
    åĿ¡
    0.25
    ç͵åŃIJ
    0.25
    hill
    0.25
    zell
    0.25
    é«ĺéĢŁ
    0.25
    riority
    0.25
    riculum
    0.25
    Activations Density 0.890%

    No Known Activations