© 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. 129533
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    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
    让åѦçĶŁ
    -0.27
    ignment
    -0.26
    亲è¿ij
    -0.25
    lopen
    -0.25
    便æĺ¯
    -0.24
    åIJķ
    -0.24
     bè
    -0.23
    iras
    -0.23
    ä¸ºä½ł
    -0.23
    elas
    -0.23
    POSITIVE LOGITS
     repeatedly
    0.53
    å¤ļ次
    0.47
     many
    0.44
     regularly
    0.43
     numerous
    0.41
     frequently
    0.41
     countless
    0.39
    å¾Īå¤ļ
    0.39
     extensively
    0.39
    许å¤ļ
    0.38
    Activations Density 34.704%

    No Known Activations