© 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. 62939
    Prev
    Next
    INDEX
    Explanations

    only

    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
    Not in Any Lists

    No Comments

    Negative Logits
    anim
    -0.27
    åįģ足
    -0.27
    UNIT
    -0.26
    icum
    -0.26
    af
    -0.25
    thin
    -0.25
    .anim
    -0.25
    auto
    -0.25
     proc
    -0.24
    æľĢåħĪè¿ĽçļĦ
    -0.24
    POSITIVE LOGITS
     deviations
    0.26
    agos
    0.25
     AppCompatActivity
    0.25
    ä¸ĸ代
    0.25
    ä¸Ģä¼ļ
    0.25
     husbands
    0.25
    stringLiteral
    0.25
    rase
    0.25
     gent
    0.24
    åģıå·®
    0.24
    Activations Density 9.349%

    No Known Activations