© 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. 112956
    Prev
    Next
    INDEX
    Explanations

    period

    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
    ç¼ĺ
    -0.28
     <![
    -0.26
    è´«
    -0.26
    该游æĪı
    -0.26
    æijĦå½±å¸Ī
    -0.25
     respectfully
    -0.24
     Corn
    -0.24
    ä¸Ģ头
    -0.24
    身影
    -0.24
    uthor
    -0.24
    POSITIVE LOGITS
     Euler
    0.28
    idal
    0.27
    棣
    0.26
    istine
    0.25
    BILE
    0.25
    iente
    0.24
    iological
    0.24
    atta
    0.24
     TableCell
    0.24
    brane
    0.24
    Activations Density 0.009%

    No Known Activations