© 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. 110929
    Prev
    Next
    INDEX
    Explanations

    Digits

    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
     correspond
    -0.26
    sap
    -0.25
    .sa
    -0.24
    æĽ´å¥½
    -0.24
    oods
    -0.24
    Editors
    -0.23
     con
    -0.23
     carrier
    -0.23
    IsNull
    -0.23
    holm
    -0.23
    POSITIVE LOGITS
    夫å¦ĩ
    0.27
    åģļ个
    0.25
    .TestCase
    0.25
    笼罩
    0.25
    TeX
    0.24
    .timing
    0.24
    .expand
    0.24
    è£ĺ
    0.24
    çݯ
    0.24
     TableRow
    0.23
    Activations Density 0.003%

    No Known Activations