© 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. 7801
    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
    åİĨ代
    -0.28
    ä¸Ģ件äºĭ
    -0.27
    å°ıä¼Ļä¼´
    -0.27
    okin
    -0.27
    å®ŀæĸ½ç»ĨåĪĻ
    -0.26
     Gutenberg
    -0.26
    好äºĭ
    -0.26
    åºĶæĢ¥ç®¡çIJĨ
    -0.26
    æīĢ以说
    -0.25
    /extensions
    -0.24
    POSITIVE LOGITS
    -effect
    0.26
    iÄĻ
    0.26
    ührung
    0.26
    icol
    0.25
    icolor
    0.25
    kker
    0.24
    -org
    0.24
     touch
    0.24
    éĿ
    0.24
    ugin
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.