© 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. 141986
    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
    æľ¬ä¹¦
    -0.28
    麸
    -0.27
     rehe
    -0.27
     Bücher
    -0.26
    bef
    -0.25
     Comparative
    -0.24
    cuda
    -0.24
    lesh
    -0.24
    åŁİåł¡
    -0.24
    (factory
    -0.23
    POSITIVE LOGITS
    izable
    0.24
    .mozilla
    0.24
    湿
    0.23
    yon
    0.23
    mans
    0.23
     mortal
    0.23
     critical
    0.23
    æĸ°åĨłèĤºçĤİ
    0.23
    ón
    0.23
     Ha
    0.23
    Activations Density 1.336%

    No Known Activations

    This feature has no known activations.