© 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. 23060
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    mph
    -0.30
    URY
    -0.27
    以ä¸ĬçļĦ
    -0.26
    à¸Ĭาย
    -0.24
    eer
    -0.24
    æ¯ķç«Ł
    -0.23
     Conan
    -0.23
    rtc
    -0.23
    .quest
    -0.23
    assertEquals
    -0.23
    POSITIVE LOGITS
    nameof
    0.28
     Remix
    0.27
    olars
    0.27
    æĿ¾
    0.26
     outgoing
    0.26
    æµģç¨ĭ
    0.25
    å¢ŀ
    0.25
    åĶ®
    0.24
     script
    0.24
    売ãĤĮ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.