© 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. 108273
    Prev
    Next
    INDEX
    Explanations

    The word "using" or "use"

    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
     nest
    -0.29
    ç²¾åįİ
    -0.26
    æĪIJè´¥
    -0.26
     <<<
    -0.25
     Ñģвоими
    -0.25
    ampion
    -0.25
    ä¹ıåĬĽ
    -0.24
    à¹Ħà¸ģล
    -0.24
     unwind
    -0.23
    uby
    -0.23
    POSITIVE LOGITS
    纳åħ¥
    0.27
    åĴĮ个人
    0.26
    è½®
    0.26
     jean
    0.26
    ICLE
    0.25
    ä¸į对
    0.25
    isas
    0.25
    orc
    0.24
    airs
    0.23
    éĿŀ常éĢĤåIJĪ
    0.23
    Activations Density 12.918%

    No Known Activations