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. 8149
    Prev
    Next
    INDEX
    Explanations

    legal documents/court appeals

    np_max-act · gemini-2.0-flash

    formal legal case captions and appellate court headers indicating jurisdiction, parties, and orders in U.S. court documents.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     encount
    -0.23
    åѸéĻ¢
    -0.23
    noinspection
    -0.23
    âĸ£
    -0.23
    ç©ij
    -0.23
    adar
    -0.23
    ä¹ĭ声
    -0.22
    izon
    -0.22
    áveis
    -0.22
     [].
    -0.22
    POSITIVE LOGITS
    ï¼Į↵
    0.66
    ,↵
    0.65
    ↵
    0.63
     ↵
    0.55
      ↵
    0.55
    \↵
    0.54
     \↵
    0.54
    "+↵
    0.52
    ï¼Į↵↵
    0.50
    -↵
    0.48
    Activations Density 0.121%

    No Known Activations