© 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. 130849
    Prev
    Next
    INDEX
    Explanations

    Risk, statistics, and comparison

    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
     everywhere
    -0.28
    ularity
    -0.28
    ores
    -0.28
    åĨį
    -0.26
    åIJĦè¡ĮåIJĦ
    -0.26
     anymore
    -0.26
    uden
    -0.26
    寸
    -0.26
    åIJĦè¡ĮåIJĦä¸ļ
    -0.25
    alia
    -0.25
    POSITIVE LOGITS
    ipo
    0.28
    _vs
    0.27
    po
    0.27
     Against
    0.27
    Against
    0.26
    åľ¨çº¿
    0.26
    bine
    0.25
    ycop
    0.25
     gegen
    0.24
    åIJij社ä¼ļ
    0.24
    Activations Density 2.409%

    No Known Activations