© 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. 6913
    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
    setWidth
    -0.31
    ibble
    -0.30
    ropy
    -0.24
    ään
    -0.24
    羡
    -0.24
    èĥ´
    -0.24
    SetName
    -0.24
     treff
    -0.23
    TypeInfo
    -0.23
    Emp
    -0.23
    POSITIVE LOGITS
    æ¯ķç«Ł
    0.30
    è³´
    0.28
    å¸Ī
    0.28
    æ¯ķç«Łæĺ¯
    0.27
    師
    0.27
    æ¼Ķ
    0.25
     display
    0.25
     displays
    0.25
    plot
    0.24
    çķ¢ç«Ł
    0.24
    Activations Density 0.087%

    No Known Activations

    This feature has no known activations.