© 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. 142702
    Prev
    Next
    INDEX
    Explanations

    body parts

    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
    :inline
    -0.28
    ãĤ·ãĥ¼ãĥ³
    -0.26
     Gul
    -0.26
    visibility
    -0.26
    åı¯è§ĨåĮĸ
    -0.25
     Crunch
    -0.24
    è¿ĺæľīä¸Ģ个
    -0.24
    CellValue
    -0.23
    åĬŁ
    -0.23
    acom
    -0.23
    POSITIVE LOGITS
    \Storage
    0.28
    æĤłæĤł
    0.27
    SJ
    0.26
    ç§ijåѦæĬĢæľ¯
    0.25
     norm
    0.25
    /socket
    0.25
     norms
    0.24
     dimension
    0.24
    norm
    0.23
    ört
    0.23
    Activations Density 15.092%

    No Known Activations