© 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. 19-TRANSCODER-HP
    7. 9017
    Prev
    Next
    INDEX
    Explanations

    answering questions

    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
    çļĦè¯Ŀ
    -0.27
    æĹĭ
    -0.26
     mentioned
    -0.24
    éĤ£ä¹Īç®Ģåįķ
    -0.24
    ä¸Ģè´¯
    -0.24
    har
    -0.23
    æľīè¿Ļæł·çļĦ
    -0.23
    íķĺìĭľ
    -0.23
     such
    -0.23
    ÑģÑĥд
    -0.23
    POSITIVE LOGITS
    íĻĢ
    0.28
    ymm
    0.26
    æĽ´æĺ¯
    0.25
    ä¸įæľį
    0.24
    ismet
    0.24
    ivet
    0.24
    owi
    0.23
     Engl
    0.23
    оваÑĤÑĮ
    0.23
    asing
    0.23
    Activations Density 1.358%

    No Known Activations