© 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. 108772
    Prev
    Next
    INDEX
    Explanations

    Code, research, legal documents

    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
    ä¾£
    -0.26
    é¾Ħ
    -0.25
    æĦı大
    -0.25
    pire
    -0.25
    贵宾
    -0.24
    ìķħ
    -0.24
     streamline
    -0.23
    Than
    -0.23
     lethal
    -0.23
     Shortcut
    -0.23
    POSITIVE LOGITS
    ä»ħä¾Ľ
    0.28
    éĿ¢ä¸´çļĦ
    0.26
     oversh
    0.25
     pers
    0.24
    yled
    0.24
    .Namespace
    0.23
    éŨæĪ·
    0.23
    opol
    0.23
     bringing
    0.23
     elev
    0.23
    Activations Density 0.182%

    No Known Activations