© 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. 22-TRANSCODER-HP
    7. 111991
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģåı¥è¯Ŀ
    -0.29
    æ¸ļ
    -0.28
    igar
    -0.26
    åĩºå±Ģ
    -0.26
    游ä¹IJ
    -0.25
    rou
    -0.24
    ç®Ķ
    -0.24
    ppo
    -0.24
    Actual
    -0.24
    orde
    -0.24
    POSITIVE LOGITS
     Canon
    0.26
    ç«ĸ
    0.26
    inality
    0.26
    æĪIJé¾Ļ
    0.25
     Hong
    0.24
     ADC
    0.24
     reserved
    0.24
     midd
    0.24
    .cfg
    0.23
    ž
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.