© 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. 108641
    Prev
    Next
    INDEX
    Explanations

    to

    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
    交代
    -0.25
    ARIO
    -0.25
    antry
    -0.25
    dl
    -0.24
    routine
    -0.24
    åĸľ
    -0.24
    doc
    -0.24
    æĬľ
    -0.23
    exe
    -0.23
    æĭĽçīĮ
    -0.23
    POSITIVE LOGITS
    è¿Ľåı£
    0.27
    Interview
    0.26
    bbe
    0.25
    ä¸Ģç±»
    0.25
    äºĭæĥħ
    0.25
    istung
    0.24
    [train
    0.24
    =train
    0.24
    BED
    0.24
     train
    0.24
    Activations Density 9.247%

    No Known Activations