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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 64266
    Prev
    Next
    INDEX
    Explanations

    Q&A, potentially technical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    第äºĮ大
    -0.35
    第äºĮ个
    -0.33
    第ä¸ī个
    -0.29
    åįģ大
    -0.28
    arya
    -0.28
    æľĢ大çļĦ
    -0.27
    itrust
    -0.27
     вÑĤоÑĢой
    -0.26
    ä¸īæĿ¡
    -0.26
    第
    -0.26
    POSITIVE LOGITS
    -cycle
    0.29
    ç«Ļç«ĭ
    0.25
    ]\\
    0.24
    ropping
    0.24
    èıī
    0.24
    æĭħ忧
    0.24
    åIJĬ顶
    0.24
    manship
    0.23
    ull
    0.23
     Frog
    0.23
    Activations Density 56.840%

    No Known Activations