© 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. 107252
    Prev
    Next
    INDEX
    Explanations

    final

    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
    奢
    -0.31
    argas
    -0.29
    ourd
    -0.24
    agine
    -0.24
    çħ§æł·
    -0.24
     plein
    -0.23
    зи
    -0.23
    ussen
    -0.23
     fores
    -0.23
    atel
    -0.23
    POSITIVE LOGITS
    peon
    0.27
    æĭľ
    0.27
    \n
    0.26
    å±ķå¼Ģ
    0.25
     consequ
    0.25
    ismatch
    0.24
    å±ķ
    0.24
    .getWriter
    0.24
    åĩı
    0.23
    remark
    0.23
    Activations Density 2.299%

    No Known Activations