© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 30470
    Prev
    Next
    INDEX
    Explanations

    tree

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æłij
    -0.37
     trees
    -0.35
     Trees
    -0.34
     tree
    -0.33
    tree
    -0.32
    TREE
    -0.32
    樹
    -0.31
    Tree
    -0.30
     Tree
    -0.30
    /tree
    -0.29
    POSITIVE LOGITS
    ä¸ŃåĽ½ä¼ģä¸ļ
    0.29
    ĵį
    0.27
    ç»ĨèĬĤ
    0.27
    æĻºæħ§åŁİå¸Ĥ
    0.26
    .getLocal
    0.26
    æĻºèĥ½
    0.25
    æĻļé¥Ń
    0.24
    {Name
    0.24
     [].
    0.24
     particulars
    0.24
    Activations Density 1.045%

    No Known Activations