© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 140540
    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
    Negative Logits
    adle
    -0.29
    伤
    -0.27
    æ°ij
    -0.26
    æĭ¿åĩº
    -0.26
    ral
    -0.26
    bout
    -0.25
    æħ¢
    -0.25
     stack
    -0.25
     mem
    -0.24
    ltr
    -0.24
    POSITIVE LOGITS
    è¿Ļä¸Ģå¹´
    0.26
    Ĥ¤
    0.26
    0.25
    -driving
    0.25
    Driving
    0.24
    缮çļĦåľ°
    0.24
    åĬ¡å®ŀ
    0.24
     DRIVE
    0.24
     Driving
    0.23
    åħĭèݱ
    0.23
    Activations Density 21.074%

    No Known Activations

    This feature has no known activations.