© 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. 19-TRANSCODER-HP
    7. 9482
    Prev
    Next
    INDEX
    Explanations

    during

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    asers
    -0.26
     BED
    -0.25
    ych
    -0.25
     insign
    -0.24
    iens
    -0.24
    æĸĩä¸Ń
    -0.23
    .credentials
    -0.23
    ements
    -0.23
     acknowled
    -0.23
    awn
    -0.23
    POSITIVE LOGITS
    çªĿ
    0.26
    -major
    0.26
     bother
    0.25
    격
    0.24
     wound
    0.24
    pics
    0.24
    endars
    0.24
    ç»ĵç®Ĺ
    0.23
     Bris
    0.23
    imization
    0.23
    Activations Density 1.298%

    No Known Activations