© 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. 64100
    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
    antro
    -0.28
    书éĿ¢
    -0.28
     <:
    -0.26
    åĨĻçĿĢ
    -0.25
    ([č↵
    -0.24
    举è¡Į
    -0.24
    idders
    -0.24
     |--
    -0.24
    riter
    -0.24
     ||č↵
    -0.23
    POSITIVE LOGITS
    æľ¬äºº
    0.30
    opic
    0.28
     personal
    0.27
    ä¾
    0.26
     py
    0.26
    Âł
    0.26
     baby
    0.26
    oss
    0.26
    éĥ¨
    0.26
     pur
    0.25
    Activations Density 52.825%

    No Known Activations

    This feature has no known activations.