© 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. 63035
    Prev
    Next
    INDEX
    Explanations

    Actions reported in studies

    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
    -0.29
    ixa
    -0.28
    ç½ijé¦ĸ页
    -0.27
    åĵĴ
    -0.25
    tsy
    -0.24
     yı
    -0.24
    esty
    -0.24
    严å¯Ĩ
    -0.23
    çķĮ第ä¸Ģ
    -0.23
    mite
    -0.23
    POSITIVE LOGITS
    Port
    0.28
    forms
    0.28
     Pg
    0.28
    Prev
    0.25
     port
    0.25
     corpor
    0.25
     Forms
    0.25
    Forms
    0.25
     forme
    0.25
     forms
    0.24
    Activations Density 10.117%

    No Known Activations