© 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. 129786
    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
    اتÙĩÙħ
    -0.26
    æĸ¤
    -0.25
    ROME
    -0.25
     NSLayoutConstraint
    -0.24
    è¿Ļ件
    -0.23
    Containing
    -0.23
     piece
    -0.23
    piece
    -0.23
    .pid
    -0.23
    çłĸ
    -0.22
    POSITIVE LOGITS
    çĶ¨å¿ĥ
    0.25
    Ĩµ
    0.25
     spiked
    0.24
    Source
    0.24
    lord
    0.23
    ume
    0.23
     scaled
    0.23
    æķĪæŀľ
    0.23
    è¯Ľ
    0.23
    åIJĮæĥħ
    0.23
    Activations Density 13.999%

    No Known Activations

    This feature has no known activations.