© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 129817
    Prev
    Next
    INDEX
    Explanations

    Legal documents and feedback

    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
    è¿ĽéŨ
    -0.29
     Govern
    -0.28
    绣é¢Ĩ
    -0.28
    å±İ
    -0.27
    æŃ¤æ¬¡
    -0.26
    è¿Ļ次
    -0.26
    æľ¬æ¬¡
    -0.26
    ertz
    -0.26
    cern
    -0.25
     Cord
    -0.25
    POSITIVE LOGITS
    rollo
    0.28
     rol
    0.27
    ç±»åŀĭçļĦ
    0.24
    çªĥ
    0.24
     outskirts
    0.24
    涩
    0.24
    人家
    0.24
    ignored
    0.24
    _YUV
    0.24
    æĢ»è§īå¾Ĺ
    0.24
    Activations Density 1.475%

    No Known Activations