© 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. 129646
    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
    åĨĴçĿĢ
    -0.28
    hek
    -0.28
    åIJ¬å¾Ĺ
    -0.25
    çĭłæĬĵ
    -0.24
    style
    -0.24
    æĬĵ
    -0.24
    æijĩ头
    -0.24
    çİĩ为
    -0.23
    åĬŁè¯¾
    -0.23
    ä½ıåľ¨
    -0.23
    POSITIVE LOGITS
    .getChannel
    0.26
    esis
    0.24
    ESIS
    0.24
    preh
    0.24
    ç¦Ĭ
    0.24
     minors
    0.23
    .reverse
    0.23
    inite
    0.23
    /*@
    0.23
    enco
    0.23
    Activations Density 1.017%

    No Known Activations

    This feature has no known activations.