© 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. 14-TRANSCODER-HP
    7. 41023
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /ros
    -0.31
    åIJ¸éĻĦ
    -0.27
    oeff
    -0.27
     logs
    -0.27
    ntl
    -0.26
    ecom
    -0.26
    è¶ĭ
    -0.24
    ç»ĵå®ŀ
    -0.24
    å²ģ
    -0.24
    trys
    -0.24
    POSITIVE LOGITS
    à¸Ľà¸£à¸°à¸Īำ
    0.27
    ä¸įåħ¬å¹³
    0.24
     YES
    0.24
    olta
    0.24
    ä¸į平衡
    0.24
    avian
    0.24
    çIJĨ解åĴĮ
    0.24
    éĺ¶æ®µæĢ§
    0.24
    éĥ¨åĪĨåĨħ容
    0.24
    _YES
    0.23
    Activations Density 0.850%

    No Known Activations

    This feature has no known activations.