© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6176
    Prev
    Next
    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    累积
    -0.29
    OTA
    -0.27
    itial
    -0.25
     rate
    -0.25
    ANCES
    -0.25
    åĬ¿
    -0.24
    åĸĦ
    -0.24
    /fw
    -0.24
    _rates
    -0.24
    第ä¸ī个
    -0.23
    POSITIVE LOGITS
     AssemblyTitle
    0.26
     Coin
    0.26
     coinc
    0.26
    åľ¨åIJĮä¸Ģ
    0.26
     hastily
    0.24
    _basename
    0.24
     useSelector
    0.24
    æĸ°åĬ¨èĥ½
    0.23
    ä¸Ģæł·
    0.23
    çļĦæĥħ
    0.23
    Activations Density 0.003%

    No Known Activations