© 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. 20-TRANSCODER-HP
    7. 107807
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ysi
    -0.28
    éķ£
    -0.28
    请注æĦı
    -0.26
    åľ°ä¸Ń
    -0.26
    注æĦı
    -0.26
    çIJĨæĥ³
    -0.26
    åīĸ
    -0.25
    /fixtures
    -0.25
    flux
    -0.24
    åħ³æ³¨
    -0.24
    POSITIVE LOGITS
    itial
    0.28
    perse
    0.26
     ded
    0.25
    caffold
    0.25
    udem
    0.24
    é»Ħèī²
    0.24
     concl
    0.23
    æį£
    0.23
     legality
    0.23
     Keystone
    0.23
    Activations Density 15.627%

    No Known Activations

    This feature has no known activations.