© 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. 63139
    Prev
    Next
    INDEX
    Explanations

    Abbreviations from online discussions

    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
    imitive
    -0.29
    åįģä¸īæĿ¡
    -0.27
    -middle
    -0.27
    amedi
    -0.25
    æĿ¡
    -0.25
    ẫu
    -0.24
    third
    -0.24
    ette
    -0.24
     propositions
    -0.24
    _crypto
    -0.24
    POSITIVE LOGITS
    verb
    0.25
    åĬ¨åijĺ
    0.24
     senses
    0.24
    ç½ijå°ıç¼ĸ
    0.24
     unseen
    0.24
    LOOK
    0.24
    åij½è¿IJ
    0.23
    ä¸Ģçľĭ
    0.23
    ç¥Ģ
    0.23
     verb
    0.23
    Activations Density 2.518%

    No Known Activations