© 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. 6842
    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
    æĸ¹éĿ¢
    -0.24
    ecd
    -0.23
     lim
    -0.23
    orsi
    -0.23
     KeyCode
    -0.23
    orean
    -0.23
    ools
    -0.23
     Libre
    -0.23
    磾
    -0.22
    chod
    -0.22
    POSITIVE LOGITS
    elige
    0.25
     Charges
    0.25
    æ°ijæĹıæĸĩåĮĸ
    0.24
    åĽºå®ļ
    0.23
    æµij
    0.23
    çªģåĩ»
    0.23
    ients
    0.23
    캡
    0.23
    èıģ
    0.22
     Pax
    0.22
    Activations Density 0.022%

    No Known Activations

    This feature has no known activations.