© 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. 64142
    Prev
    Next
    INDEX
    Explanations

    names and locations

    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
    NZ
    -0.28
     Reviewed
    -0.27
     proportion
    -0.27
     lump
    -0.26
     usually
    -0.24
    .setCellValue
    -0.24
     (%)
    -0.24
    *q
    -0.23
    nez
    -0.23
    ãģ¾ãģ¾
    -0.23
    POSITIVE LOGITS
    åĥıæĺ¯
    0.29
    åĽĽé¡¹
    0.27
    !/
    0.26
    æľīä»·åĢ¼çļĦ
    0.26
    ynet
    0.26
    ªĮ
    0.25
    actices
    0.25
     Hath
    0.25
     tÆ°
    0.25
    两项
    0.24
    Activations Density 32.136%

    No Known Activations