© 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. 12-TRANSCODER-HP
    7. 23008
    Prev
    Next
    INDEX
    Explanations

    Computer code and legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    undo
    -0.29
    çļĦå°±æĺ¯
    -0.27
    opies
    -0.26
    缮
    -0.26
    æ¡¥æ¢ģ
    -0.26
    seealso
    -0.26
     interim
    -0.25
     singly
    -0.25
     objective
    -0.24
     loft
    -0.24
    POSITIVE LOGITS
    /posts
    0.26
    YA
    0.26
    顺
    0.25
    ä¸ĢæŦ
    0.25
    /MIT
    0.25
    è¿Ļç¯ĩæĸĩç«ł
    0.25
    ----------</
    0.24
    ermal
    0.24
     ClassNotFoundException
    0.24
    èĮħ
    0.23
    Activations Density 0.009%

    No Known Activations