© 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. 18-TRANSCODER-HP
    7. 89025
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umer
    -0.30
    лиÑĤ
    -0.30
     phục
    -0.28
    ëĮĦ
    -0.28
    ç±į
    -0.25
     infinit
    -0.25
    æĹłç¼Ŀ
    -0.24
    æĸŃ
    -0.24
    ãģķãģĦ
    -0.24
    ä¸Ģæī¹
    -0.24
    POSITIVE LOGITS
    éĢ»è¾ij
    0.25
     unthinkable
    0.24
     logic
    0.24
    çľĭçľĭ
    0.24
     blanks
    0.24
    !";↵
    0.24
    Dig
    0.24
    æ°§
    0.23
    oleon
    0.23
     parsley
    0.23
    Activations Density 27.042%

    No Known Activations