© 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. 141827
    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
    主æĦı
    -0.25
    ANE
    -0.25
    èĢľ
    -0.24
    âĤĬ
    -0.24
     Fol
    -0.24
    æĸ°éĹ»ç½ij
    -0.24
    rians
    -0.24
    AML
    -0.24
    meg
    -0.23
    izen
    -0.23
    POSITIVE LOGITS
    çļĦéĤ£ç§į
    0.27
    亢
    0.25
     hun
    0.24
    çį¾
    0.24
    éĤ£ç§į
    0.24
    æīįä¼ļ
    0.23
     dams
    0.23
    ä¸įåıªæĺ¯
    0.23
    åĪļå¼Ģå§ĭ
    0.23
    Em
    0.23
    Activations Density 4.419%

    No Known Activations

    This feature has no known activations.