© 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. 107570
    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
    è¿Ļ两天
    -0.29
     glBegin
    -0.26
    ç»ĦåĽ¢
    -0.26
    æĺ¯çĶ¨æĿ¥
    -0.26
    è´¡
    -0.26
    太é«ĺ
    -0.25
     kans
    -0.25
    -sizing
    -0.24
     élev
    -0.23
     testName
    -0.23
    POSITIVE LOGITS
    n
    0.27
    vert
    0.24
    åı°
    0.24
     param
    0.24
    acre
    0.23
    aina
    0.23
     Training
    0.23
    åķ¼
    0.23
     hard
    0.23
    åı°ä¸Ĭ
    0.23
    Activations Density 1.570%

    No Known Activations

    This feature has no known activations.