© 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. 108628
    Prev
    Next
    INDEX
    Explanations

    Dates and time periods

    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
    ç»Īäºİ
    -0.27
     Reyn
    -0.26
    å°ıå¾®
    -0.26
    æ¸Ĭ
    -0.25
    ä¹ŁçŁ¥éģĵ
    -0.25
    alue
    -0.24
    LICENSE
    -0.24
    éģĩä¸Ĭ
    -0.24
    å¥ĸåĬ±
    -0.24
     moy
    -0.24
    POSITIVE LOGITS
    ffe
    0.27
    èĽŃ
    0.27
    SION
    0.27
    Duplicate
    0.26
    -place
    0.25
     dio
    0.24
    _duplicate
    0.24
     libero
    0.24
     Emanuel
    0.24
    ÐĿÐĺ
    0.24
    Activations Density 4.472%

    No Known Activations