© 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. 88738
    Prev
    Next
    INDEX
    Explanations

    Technical/internet abbreviations?

    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
    çļĦåıijå±ķ
    -0.27
    ucch
    -0.25
    åģļèµ·
    -0.25
    -tools
    -0.24
    åĪ·
    -0.24
    _tools
    -0.23
     Receive
    -0.23
    çīµ
    -0.23
    æĹłæĦı
    -0.23
     Ranking
    -0.23
    POSITIVE LOGITS
    ograms
    0.31
    .gwt
    0.28
     Sammy
    0.27
     courses
    0.27
    iane
    0.27
     {.
    0.25
    /question
    0.24
    éĩįä¸Ń
    0.24
     //////////////////////////////////////////////////////////////////////
    0.24
     sinon
    0.23
    Activations Density 0.038%

    No Known Activations