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. 162703
    Prev
    Next
    INDEX
    Explanations

    phot

    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
    erton
    -0.28
    urface
    -0.27
    erta
    -0.26
    èIJ¥åħ»
    -0.26
    ie
    -0.25
    erte
    -0.25
    neau
    -0.25
    lists
    -0.25
    oyo
    -0.24
    axon
    -0.24
    POSITIVE LOGITS
    æĪIJ交
    0.31
    iken
    0.30
    å¼ķæĵİ
    0.28
    欢è¿İ
    0.26
    anza
    0.26
    CONTEXT
    0.25
    ilk
    0.24
    æłħ
    0.24
    ek
    0.24
    ÑĥÑĪки
    0.24
    Activations Density 0.001%

    No Known Activations