© 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. 140663
    Prev
    Next
    INDEX
    Explanations

    as

    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
     estates
    -0.28
    -pin
    -0.25
    -cycle
    -0.25
    åIJĮè¡Į
    -0.25
     mates
    -0.25
    .Static
    -0.24
    primer
    -0.24
    çİĩ为
    -0.24
    ÙĪÙģ
    -0.23
    è°Ķ
    -0.23
    POSITIVE LOGITS
    asion
    0.28
    çĤ¸å¼¹
    0.27
    éĽĨè£ħ
    0.27
    ä¸Ńå°ı
    0.26
    Ace
    0.26
     Authors
    0.25
    è°ĥ
    0.25
    æĭĽèģĺä¿¡æģ¯
    0.25
    ç»ıèIJ¥æ¨¡å¼ı
    0.25
     {{--<
    0.24
    Activations Density 14.648%

    No Known Activations