© 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. 62852
    Prev
    Next
    INDEX
    Explanations

    Code and technical 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
    Not in Any Lists

    No Comments

    Negative Logits
    ilon
    -0.27
     Liquid
    -0.25
    éĺĩ
    -0.25
    outu
    -0.24
     storm
    -0.24
    FileSystem
    -0.23
    obili
    -0.23
    å¹³éĿĻ
    -0.23
    antom
    -0.23
    åħ¨ä½ĵ
    -0.23
    POSITIVE LOGITS
    trust
    0.24
    å®ļæľŁ
    0.24
    empt
    0.24
    åįĴ
    0.24
    advisor
    0.24
    usch
    0.24
    æľĢåħĪè¿ĽçļĦ
    0.24
    æĭ¨
    0.24
     neglect
    0.24
    æľĢæĸ°çļĦ
    0.24
    Activations Density 2.942%

    No Known Activations