© 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. 64626
    Prev
    Next
    INDEX
    Explanations

    Technical documentation and research

    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
     esp
    -0.33
    erial
    -0.28
    ä¸Ńåľº
    -0.27
     esl
    -0.24
     Esp
    -0.24
     CP
    -0.24
     Polar
    -0.24
    iffer
    -0.24
    .getTable
    -0.24
    cp
    -0.24
    POSITIVE LOGITS
    nü
    0.27
    поÑĤ
    0.25
    mage
    0.25
    _fa
    0.24
    .defaults
    0.24
    bigint
    0.24
    mó
    0.23
    ếc
    0.23
    åĽĬ
    0.23
     zwar
    0.23
    Activations Density 4.369%

    No Known Activations