© 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. 130931
    Prev
    Next
    INDEX
    Explanations

    million

    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
    çİĭæľĿ
    -0.30
    æĬķ
    -0.30
    CAS
    -0.28
    ini
    -0.28
     AUTHOR
    -0.26
    çķ¸
    -0.26
    Cas
    -0.25
     Alic
    -0.24
    utters
    -0.24
    sı
    -0.24
    POSITIVE LOGITS
     dug
    0.28
     or
    0.27
    elp
    0.26
     underst
    0.25
    .Positive
    0.25
     age
    0.24
    IfExists
    0.23
    .createComponent
    0.23
    /kubernetes
    0.23
    PageIndex
    0.23
    Activations Density 21.360%

    No Known Activations