© 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. 19-TRANSCODER-HP
    7. 8378
    Prev
    Next
    INDEX
    Explanations

    data/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .addColumn
    -0.28
    èĮij
    -0.26
     NSK
    -0.25
    ution
    -0.24
    oves
    -0.23
    USAGE
    -0.23
     mars
    -0.23
     Unt
    -0.23
    æijĨ
    -0.23
     }</
    -0.23
    POSITIVE LOGITS
    à¹Īา
    0.29
    ÑģоÑģ
    0.26
     implied
    0.25
    -ended
    0.24
    ýt
    0.24
    åłª
    0.24
    .stub
    0.23
     Pickup
    0.23
     wealth
    0.23
    å·²ç»ıæľīäºĨ
    0.23
    Activations Density 0.005%

    No Known Activations