© 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. 130521
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations, numbers

    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
    æĮĤ
    -0.24
     human
    -0.24
    è§Ĩè§ī
    -0.23
    管线
    -0.22
     resc
    -0.22
    ç»Ħç»ĩå®ŀæĸ½
    -0.21
    临è¿ij
    -0.21
    :start
    -0.21
    reau
    -0.21
    æľīäºĨ
    -0.21
    POSITIVE LOGITS
     Redistributions
    0.25
    (ft
    0.24
    ointed
    0.24
    yard
    0.23
    èĿĩ
    0.23
    -ft
    0.23
    ä¸ĭ乡
    0.23
    tent
    0.22
    ernet
    0.22
     Priv
    0.21
    Activations Density 75.969%

    No Known Activations