© 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. 89686
    Prev
    Next
    INDEX
    Explanations

    Programming questions and answers

    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
    åIJİç»Ń
    -0.30
    º«
    -0.28
    ç¬ijèĦ¸
    -0.27
    åIJĮæł·çļĦ
    -0.27
    izzo
    -0.26
     Chancellor
    -0.26
    .Sm
    -0.26
    	finally
    -0.25
    缸åIJĮçļĦ
    -0.25
     subsequent
    -0.24
    POSITIVE LOGITS
    åħĪ
    0.29
     preced
    0.28
     prelim
    0.28
    æĭįåįĸ
    0.27
     beforehand
    0.27
    è¿ĩé«ĺ
    0.26
     foresee
    0.25
    hands
    0.25
     trừ
    0.25
    trx
    0.25
    Activations Density 28.717%

    No Known Activations