© 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. 130477
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     pur
    -0.31
     shared
    -0.30
     suits
    -0.29
    åħ±åIJĮ
    -0.28
    equal
    -0.27
     equal
    -0.27
    ji
    -0.27
    Ky
    -0.26
     equality
    -0.26
    ipro
    -0.26
    POSITIVE LOGITS
    åĮĸçļĦ
    0.30
    æľīåĩłä¸ª
    0.27
    æĸĿ
    0.26
    äºĨä»ĸçļĦ
    0.26
    åĩºæĿ¥çļĦ
    0.26
    ASON
    0.26
    åĮĸè¿Ľç¨ĭ
    0.26
    ousel
    0.26
    äºĨ个
    0.26
    ä¸įåıĹ
    0.25
    Activations Density 12.506%

    No Known Activations