© 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. 130336
    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
    undi
    -0.29
    ichte
    -0.25
    ful
    -0.24
    é«ĺè´µ
    -0.24
    æħ¨
    -0.24
    IGH
    -0.23
     exposes
    -0.23
     cont
    -0.23
    .openapi
    -0.23
     geg
    -0.23
    POSITIVE LOGITS
    engo
    0.34
    -corner
    0.28
    ä¸Ģç¯ĩæĸĩç«ł
    0.27
    èĤ²åĦ¿
    0.26
    æģ¶æĦı
    0.26
     configuring
    0.26
    ä¸Ģæłĭ
    0.25
    entin
    0.24
    ä¸Ģ身
    0.23
    å©¢
    0.23
    Activations Density 11.470%

    No Known Activations

    This feature has no known activations.