© 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. 108071
    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
    itin
    -0.28
    emy
    -0.28
    .ag
    -0.28
    æĪIJç«ĭ
    -0.28
    abh
    -0.26
    çĽ¹
    -0.26
    ä½Ĩæĺ¯å¦Ĥæŀľ
    -0.26
    enson
    -0.25
     sigma
    -0.25
    è¨Ĥ
    -0.25
    POSITIVE LOGITS
    uce
    0.31
     %@
    0.28
    .substr
    0.28
     %@",
    0.28
    æĮŁ
    0.27
    arcer
    0.27
    碧
    0.27
    ustr
    0.27
    æĢ»èµĦ产
    0.26
    lassen
    0.26
    Activations Density 0.987%

    No Known Activations

    This feature has no known activations.