© 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. 108095
    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
    suming
    -0.31
    urst
    -0.28
    stay
    -0.28
    akit
    -0.26
    wap
    -0.26
     remained
    -0.25
    ateral
    -0.25
    å¹´è½»çļĦ
    -0.24
    ominated
    -0.24
    ToAdd
    -0.24
    POSITIVE LOGITS
    åħħ
    0.33
    鼶
    0.25
    æŀģ
    0.24
    lh
    0.24
    æĮģ
    0.23
    .icons
    0.23
    丰满
    0.23
    _Cell
    0.23
    hé
    0.23
    fra
    0.22
    Activations Density 15.775%

    No Known Activations

    This feature has no known activations.