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. 162718
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ainers
    -0.27
    è£ħ
    -0.27
    .iteritems
    -0.26
    abelle
    -0.26
    翻身
    -0.26
    罩
    -0.25
    Pair
    -0.24
     meshes
    -0.24
    gan
    -0.24
    ophon
    -0.24
    POSITIVE LOGITS
    quest
    0.30
    åı£æ°´
    0.28
    meric
    0.27
    iler
    0.27
    羣å®ŀçļĦ
    0.26
    meer
    0.26
     delt
    0.25
    个人信æģ¯
    0.25
    för
    0.25
    ç¦ıå¾·
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.