© 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
    2. Qwen3-4B
    3. 19-TRANSCODER-HP
    4. 6044
    Prev
    Next
    INDEX
    Explanations

    programming and casual text

    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
    wig
    -0.30
    第ä¸ĢæĿ¡
    -0.29
    ÑĢÑıд
    -0.28
    ÑĪка
    -0.28
    mers
    -0.26
    çļĦç«ŀäºī
    -0.26
    éĨļ
    -0.25
    ç«ŀäºī
    -0.25
    epam
    -0.25
    ulative
    -0.25
    POSITIVE LOGITS
    åį±
    0.32
    ocity
    0.29
    udder
    0.28
     cut
    0.28
     unavoidable
    0.27
     simulated
    0.26
    **
    0.26
    åĬ²
    0.26
     limit
    0.26
     swallow
    0.25
    Activations Density 0.005%

    No Known Activations