© 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. 64682
    Prev
    Next
    INDEX
    Explanations

    a or an

    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
    ummings
    -0.27
     descon
    -0.27
    unce
    -0.26
     vistas
    -0.25
     Hanging
    -0.25
    horn
    -0.25
    æĤ¬æĮĤ
    -0.25
    ç§ijæĬĢèĤ¡ä»½
    -0.25
     Pending
    -0.25
    stitutions
    -0.24
    POSITIVE LOGITS
     punishable
    0.26
     site
    0.26
    Operator
    0.26
    LIKE
    0.26
    ivable
    0.26
    Sites
    0.25
    .Operator
    0.25
    ãĤµãĤ¤ãĥĪ
    0.24
    .imp
    0.24
     editable
    0.24
    Activations Density 10.412%

    No Known Activations