© 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. 129708
    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
     Hour
    -0.29
     hour
    -0.25
    aign
    -0.25
    ocode
    -0.25
    enen
    -0.24
    asion
    -0.24
     void
    -0.23
    walker
    -0.23
    /forum
    -0.23
     flotation
    -0.23
    POSITIVE LOGITS
    pot
    0.30
    ä¸įæŃ»
    0.28
     sled
    0.28
     Seat
    0.27
    quÃŃ
    0.26
    ä¸Ģ大æī¹
    0.26
    æľįä»İ
    0.26
     seats
    0.25
    gom
    0.25
    å¿łå®ŀ
    0.25
    Activations Density 2.357%

    No Known Activations

    This feature has no known activations.