© 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. 129094
    Prev
    Next
    INDEX
    Explanations

    research papers

    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
    lä
    -0.27
    ugal
    -0.27
    ellan
    -0.25
    æĢ»è£ģ
    -0.25
    erator
    -0.25
    isen
    -0.25
    æĹłåı¯
    -0.25
    <<<
    -0.24
    æĦıå¤ĸ
    -0.24
    FieldValue
    -0.23
    POSITIVE LOGITS
    zas
    0.26
    ("?
    0.25
    coord
    0.24
    fers
    0.24
    fl
    0.23
    ifle
    0.23
     flattering
    0.23
     admire
    0.23
    stage
    0.23
     balances
    0.23
    Activations Density 0.182%

    No Known Activations