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. 53851
    Prev
    Next
    INDEX
    Explanations

    Historical events/dates

    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
    æĮ½
    -0.30
     Mood
    -0.28
    ral
    -0.28
    uct
    -0.26
    $title
    -0.26
    èģĮæĿĥ
    -0.26
     onCreateViewHolder
    -0.26
    ensual
    -0.25
    omatic
    -0.24
    ä¼łåĩº
    -0.24
    POSITIVE LOGITS
    åĨľè´¸
    0.27
    å¤ıåŃ£
    0.27
    åŁł
    0.26
    è¿ģç§»
    0.26
    acht
    0.25
    prises
    0.25
     *[
    0.24
    ä¸įåħĭ
    0.24
    çļĦå®īåħ¨
    0.24
    izens
    0.24
    Activations Density 0.002%

    No Known Activations