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. 54595
    Prev
    Next
    INDEX
    Explanations

    company types

    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
    注æĺİæĿ¥æºIJ
    -0.30
    antine
    -0.27
    çĽĸ
    -0.27
    à¹Ģà¸Ĺ
    -0.27
    计
    -0.27
     volumes
    -0.26
    adera
    -0.26
    ADE
    -0.26
     ÑĤÑĢÑĥд
    -0.26
     hood
    -0.25
    POSITIVE LOGITS
    .flush
    0.30
    èĭĮ
    0.26
     Equality
    0.26
    asu
    0.26
    agar
    0.26
    idl
    0.25
    åīª
    0.25
    åij¼
    0.24
    =cut
    0.24
    ushing
    0.24
    Activations Density 0.013%

    No Known Activations