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. 72940
    Prev
    Next
    INDEX
    Explanations

    Code/Tech

    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
    ask
    -0.27
    addle
    -0.27
    ago
    -0.26
    plementary
    -0.26
    让æĤ¨
    -0.26
    arf
    -0.25
    纲
    -0.25
     ConfigureServices
    -0.24
    asks
    -0.24
    ango
    -0.24
    POSITIVE LOGITS
    ()",
    0.25
     "*",
    0.25
    BED
    0.25
     PF
    0.24
    飵
    0.24
    ()',
    0.24
    .mozilla
    0.23
     dessert
    0.23
    OX
    0.23
     veil
    0.23
    Activations Density 0.061%

    No Known Activations