© 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. 112991
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    thouse
    -0.26
    Toolkit
    -0.25
     sums
    -0.24
     Fucked
    -0.24
    MEA
    -0.24
    entine
    -0.23
    curities
    -0.23
    Ñīей
    -0.23
     Bitcoins
    -0.23
    uffles
    -0.23
    POSITIVE LOGITS
    ä¸Ģç»ı
    0.28
    овал
    0.25
    æ°ĺ
    0.25
    çĻ»éĮĦ
    0.25
    ç§ijå°Ķ
    0.25
    oter
    0.24
    apo
    0.24
    橱
    0.24
    æļ´åĬĽ
    0.23
    mer
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.