© 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. 106800
    Prev
    Next
    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash
    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
    éĺ»
    -0.28
    æĭ©
    -0.28
    é¤IJ
    -0.26
    è¡£
    -0.24
    ect
    -0.24
    ct
    -0.24
    ....↵↵
    -0.24
    обÑĢ
    -0.24
    æľĢå°ij
    -0.24
    åĪº
    -0.24
    POSITIVE LOGITS
    åľ°çľĭçĿĢ
    0.27
    è¨ĺèĢħ
    0.26
     Belgi
    0.26
     uninsured
    0.25
    ãģĴ
    0.24
    .drag
    0.24
    GMEM
    0.24
     Accord
    0.24
    drag
    0.23
    赶ä¸Ĭ
    0.23
    Activations Density 3.475%

    No Known Activations