© 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. 8818
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ulp
    -0.32
     tua
    -0.27
    riger
    -0.26
    po
    -0.25
    enza
    -0.25
    unas
    -0.25
    кÑĥп
    -0.25
    qu
    -0.25
    ARIO
    -0.25
    .onload
    -0.24
    POSITIVE LOGITS
    Against
    0.27
     Against
    0.27
    ä»ĬæĻļ
    0.25
     normally
    0.25
    çİ°åľ¨å¾Īå¤ļ
    0.24
    mods
    0.23
    ãģĦãģ¾
    0.23
    äºĶä¸Ģ
    0.23
    ä½ķåĨµ
    0.23
    æѤåĪ»
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.