© 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. 141806
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ç½ijç»ľä¼łæĴŃ
    -0.30
    æĶ¸
    -0.28
     nameof
    -0.27
    åįĸç»Ļ
    -0.26
    fft
    -0.25
    交ç»Ļ
    -0.25
    dez
    -0.24
     artık
    -0.24
    vertise
    -0.24
    volution
    -0.24
    POSITIVE LOGITS
    ivers
    0.29
    å¾Ī好çļĦ
    0.25
    ives
    0.25
     concurrent
    0.25
     spir
    0.25
    atom
    0.25
    两级
    0.25
     Spir
    0.24
    _DOC
    0.24
    ifs
    0.24
    Activations Density 20.511%

    No Known Activations