© 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. 22-TRANSCODER-HP
    7. 129679
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¡ı
    -0.27
    é¢ľ
    -0.27
    _wc
    -0.23
    åħ¨å¤©
    -0.22
    wcs
    -0.22
    ForResource
    -0.22
    åIJİçļĦ
    -0.21
    elsey
    -0.21
    .BorderStyle
    -0.21
    æĤ¬å´ĸ
    -0.21
    POSITIVE LOGITS
    æĹ¥åľ¨
    0.24
    ","+
    0.24
    æĭ¿äºĨ
    0.23
    ä»ĸåľ¨
    0.23
    /as
    0.23
    æĭ¿åĩº
    0.22
    -Jul
    0.22
    åĽ¢éķ¿
    0.22
     synth
    0.22
    æĭ¿åĪ°
    0.22
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.