© 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. 8780
    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
    aken
    -0.26
    ARK
    -0.26
    æ¯ıä¸Ģ天
    -0.25
    -pill
    -0.25
    ktop
    -0.25
    ÑĢаÑī
    -0.25
     watch
    -0.25
     foundation
    -0.24
     bulls
    -0.24
     angular
    -0.23
    POSITIVE LOGITS
    çļĦæīĭ
    0.31
    æīĭ
    0.29
    æĸ¹éĿ¢çļĦ
    0.29
    è¿ĩç¨ĭ
    0.28
    ç¢İ
    0.27
    æĸ¹éĿ¢
    0.27
    æĸ¹åIJij
    0.26
    çºł
    0.25
    çļĦè¿ĩç¨ĭ
    0.24
    æīĭåĬ¨
    0.24
    Activations Density 0.065%

    No Known Activations

    This feature has no known activations.