© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6595
    Prev
    Next
    INDEX
    Explanations

    Technical documents/code

    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
    èĽ¾
    -0.29
    çļĦ游æĪı
    -0.25
     High
    -0.25
    ameda
    -0.24
    å¯Į
    -0.24
     vbox
    -0.24
    /graphql
    -0.24
    rix
    -0.24
    æĶ¿çŃĸæݪæĸ½
    -0.24
    icated
    -0.23
    POSITIVE LOGITS
    è¾ĥå·®
    0.35
    åĬ£
    0.34
     kém
    0.33
    ç²Ĺç³Ļ
    0.32
    èĸĦå¼±
    0.31
     shortcomings
    0.30
    å¾Īå·®
    0.30
     weak
    0.30
    å¼±
    0.29
    æĭĻ
    0.29
    Activations Density 0.264%

    No Known Activations