© 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. 7839
    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
    ä¸įä¼ļåĨį
    -0.27
     sprung
    -0.24
    对åŃ©åŃIJ
    -0.23
    енн
    -0.23
    jax
    -0.23
    åĪºå®¢
    -0.22
    inch
    -0.22
    tÃŃ
    -0.22
    dependencies
    -0.22
     descendant
    -0.22
    POSITIVE LOGITS
    éķľ
    0.27
     вÑħод
    0.25
    orge
    0.24
    使çĶ¨èĢħ
    0.24
     erection
    0.24
    æľºç»Ħ
    0.24
    èĢħ
    0.24
    orate
    0.24
    brane
    0.24
    nie
    0.24
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.