© 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. 7759
    Prev
    Next
    INDEX
    Explanations

    technical terminology

    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
    éĺ¡
    -0.24
    extr
    -0.24
    ç¾ļ
    -0.24
    Editors
    -0.23
    /Graphics
    -0.23
    å¸ĤæĶ¿åºľ
    -0.23
    ÇĴ
    -0.23
    .setX
    -0.23
    ';
    -0.22
    åĨįå¤ļ
    -0.22
    POSITIVE LOGITS
     minded
    0.28
    моÑĢ
    0.27
    iali
    0.27
    ãģķãģĪ
    0.25
    çķľ
    0.24
    åĪĹ
    0.24
    calls
    0.24
    å·´å·´
    0.24
    cket
    0.24
    esti
    0.24
    Activations Density 0.035%

    No Known Activations