© 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. 7953
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     purpos
    -0.28
    æĢľ
    -0.28
    illery
    -0.28
     zosta
    -0.27
     coursework
    -0.27
     Provided
    -0.26
    plevel
    -0.24
     ruth
    -0.24
     Pillow
    -0.24
    ä¸Ģçľ¼
    -0.24
    POSITIVE LOGITS
    uit
    0.34
    este
    0.28
    van
    0.28
    饱åĴĮ
    0.28
    uits
    0.27
    fan
    0.27
    eman
    0.26
     inv
    0.26
    Native
    0.26
    :Register
    0.25
    Activations Density 0.125%

    No Known Activations

    This feature has no known activations.