© 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. 22-TRANSCODER-HP
    7. 86805
    Prev
    Next
    INDEX
    Explanations

    Starting or introductory phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ç´¢
    -0.26
    è¿ĩåĪĨ
    -0.26
    uml
    -0.25
    èĦī
    -0.25
    à´¯
    -0.25
    å¥Ĺ
    -0.25
    â
    -0.25
    .Pre
    -0.24
    æ©Ľ
    -0.24
    ι
    -0.24
    POSITIVE LOGITS
    (_,
    0.25
    äºĭåĦ¿
    0.25
    IEWS
    0.25
    æĦıæĢĿæĺ¯
    0.24
    nesty
    0.24
    neys
    0.24
    nesota
    0.24
    éªĪ
    0.24
    ä¸Ģç¬Ķ
    0.24
    åıĤ
    0.24
    Activations Density 0.008%

    No Known Activations