© 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. 8262
    Prev
    Next
    INDEX
    Explanations

    Jersey

    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
    åѦçĶŁä»¬
    -0.28
    ç®ķ
    -0.25
    odos
    -0.25
    Rails
    -0.24
    npos
    -0.24
    æ²Ļåıijä¸Ĭ
    -0.24
     Ãħ
    -0.24
    hap
    -0.23
     Gron
    -0.23
    mpl
    -0.23
    POSITIVE LOGITS
    scription
    0.27
    ç±į
    0.26
    头
    0.26
    .âĢ¢
    0.25
    åľ¨æѤ
    0.24
    æľ¬äºº
    0.24
     <![
    0.24
     duy
    0.23
    cket
    0.23
    /she
    0.23
    Activations Density 0.527%

    No Known Activations