© 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. 8038
    Prev
    Next
    INDEX
    Explanations

    present

    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
    visa
    -0.31
    奥æŀĹåĮ¹åħĭ
    -0.28
    ↵            ↵
    -0.26
    fleet
    -0.26
    erras
    -0.25
     mÃŃn
    -0.25
    åĽŃ
    -0.25
    åIJ¦
    -0.24
     slightest
    -0.24
    ↵     ↵
    -0.24
    POSITIVE LOGITS
     interior
    0.27
    æĪijåıĪ
    0.27
    WISE
    0.25
     inputFile
    0.25
    ãģ¡ãģª
    0.25
    apore
    0.24
     Interior
    0.24
     ìłľê°Ģ
    0.24
    ãģıãĤĮ
    0.24
     setC
    0.24
    Activations Density 0.001%

    No Known Activations