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. 11-TRANSCODER-HP
    4. 47248
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isman
    -0.27
    tober
    -0.27
    æĭīæĸ¯
    -0.26
     HPV
    -0.26
    驾车
    -0.24
     steady
    -0.23
    енÑĮ
    -0.23
    äºĨä¸Ģåı£æ°Ķ
    -0.23
    ings
    -0.23
    ä¸į让
    -0.23
    POSITIVE LOGITS
     Dou
    0.29
     irc
    0.26
    ough
    0.25
    ouns
    0.25
    毫米
    0.25
     exist
    0.25
    IfExists
    0.25
    éļı
    0.24
    Inserted
    0.24
    毫
    0.23
    Activations Density 0.140%

    No Known Activations