© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6838
    Prev
    Next
    INDEX
    Explanations

    Quotations and code snippets

    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
    âĤ¬âĦ¢
    -0.27
    ors
    -0.27
     cluster
    -0.27
     tick
    -0.27
     musical
    -0.25
     non
    -0.25
    æĬĦ
    -0.25
    -camera
    -0.25
    ong
    -0.24
    ä¸Ńæĸ¹
    -0.24
    POSITIVE LOGITS
    ä¸ĢäºĮ
    0.27
    -Cs
    0.26
    æĹ¶è¡¨ç¤º
    0.26
     ^(
    0.25
    ªĮ
    0.25
    ULA
    0.25
    @stop
    0.25
    建ç«ĭ
    0.25
    .Values
    0.24
    åħį责声æĺİ
    0.24
    Activations Density 0.085%

    No Known Activations