© 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. 89729
    Prev
    Next
    INDEX
    Explanations

    research

    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
     nguyên
    -0.28
    Margin
    -0.26
    asse
    -0.25
     Margin
    -0.25
     @{↵
    -0.25
     cheats
    -0.24
    ufen
    -0.24
    ÙĦد
    -0.24
    -origin
    -0.24
    èİħ
    -0.23
    POSITIVE LOGITS
    å¿ħ
    0.27
    ä¸Ģå®ļæĺ¯
    0.26
    .builders
    0.25
    éĥ½çŁ¥éģĵ
    0.24
     obvious
    0.24
    æĢİä¹Īçľĭ
    0.24
     conduc
    0.24
     inevitably
    0.24
     jScrollPane
    0.24
    稿件
    0.24
    Activations Density 21.755%

    No Known Activations