© 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. 8709
    Prev
    Next
    INDEX
    Explanations

    News/reporting

    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
    wp
    -0.34
    Priv
    -0.28
    priv
    -0.28
    é¹ı
    -0.26
    dent
    -0.25
     sonst
    -0.24
     prive
    -0.24
    .pen
    -0.24
     pry
    -0.23
    eced
    -0.23
    POSITIVE LOGITS
    çļĦåIJĦ项
    0.28
    çļĦéĤ£ä¸ª
    0.28
    çļĦéĤ£ä¸Ģ
    0.26
     cheated
    0.25
    reau
    0.25
    felt
    0.24
     batching
    0.24
    åıĺå½¢
    0.24
    -prev
    0.24
    ogra
    0.24
    Activations Density 0.040%

    No Known Activations