© 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. 8658
    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
    uated
    -0.28
    人æĢ§
    -0.27
    çķľ
    -0.27
    æĬij
    -0.26
    æģ¢
    -0.26
    è¯ĹæŃĮ
    -0.25
    oustic
    -0.25
    FileSync
    -0.24
    é«ĺæ½®
    -0.24
    /plain
    -0.24
    POSITIVE LOGITS
    letics
    0.28
     Monthly
    0.26
    éĢĭ
    0.26
    xfa
    0.25
    设æĸ½å»ºè®¾
    0.25
    åIJĦé¡¹å·¥ä½ľ
    0.25
    .lt
    0.25
    -->↵
    0.24
    -coded
    0.24
    -->č↵
    0.24
    Activations Density 0.015%

    No Known Activations

    This feature has no known activations.