© 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. 64406
    Prev
    Next
    INDEX
    Explanations

    Code or technical contexts

    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
    INCLUDED
    -0.28
     EITHER
    -0.27
    BarItem
    -0.27
    ,ID
    -0.27
    chwitz
    -0.27
    åĽºå®ļçļĦ
    -0.27
    æĪijæĺ¯
    -0.27
    .toolbox
    -0.27
    åİŁæĿ¥æĺ¯
    -0.26
    满æĦıçļĦ
    -0.26
    POSITIVE LOGITS
    uje
    0.27
    outs
    0.26
    ats
    0.26
     don
    0.26
     and
    0.26
    occ
    0.25
    åĴĮ社ä¼ļ
    0.25
    os
    0.25
    ish
    0.25
     context
    0.25
    Activations Density 9.022%

    No Known Activations