© 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. 141715
    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
    trinsic
    -0.29
     bottleneck
    -0.28
    ensa
    -0.27
    endent
    -0.25
     bott
    -0.25
    mine
    -0.25
    ported
    -0.24
    iol
    -0.24
    soles
    -0.24
     Stones
    -0.24
    POSITIVE LOGITS
    avana
    0.27
    IMER
    0.25
     unbe
    0.25
    åIJĪä½ľ
    0.24
    UpDown
    0.24
    ç«ĭåĪ»
    0.24
    æĽĻ
    0.24
    .rev
    0.23
    åįıä¼ļ
    0.23
    association
    0.23
    Activations Density 19.271%

    No Known Activations

    This feature has no known activations.