© 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. 6863
    Prev
    Next
    INDEX
    Explanations

    Question answering context

    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
    è¿Ļç§įæĸ¹å¼ı
    -0.35
    è¿Ļæł·åģļ
    -0.35
    egas
    -0.30
    åĸ·
    -0.27
    essor
    -0.27
    ãģĿãģĨ
    -0.26
    ilit
    -0.26
    ög
    -0.24
    æŃ¤ä¸¾
    -0.24
     airs
    -0.23
    POSITIVE LOGITS
    æĺ¯çĶ¨æĿ¥
    0.26
    flashdata
    0.26
    imagem
    0.26
    Invocation
    0.25
    ä¸ŃæľĢ
    0.24
     itself
    0.24
    çªĿ
    0.24
    çļĦæł¸å¿ĥ
    0.23
    åĢĺ
    0.23
    å¦Ĥä½ķåİ»
    0.23
    Activations Density 0.407%

    No Known Activations