© 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. 99048
    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
    ddf
    -0.27
    太平
    -0.26
    ows
    -0.24
    å¾Ĺèµ·
    -0.23
     mapper
    -0.23
    ofire
    -0.23
     tangent
    -0.23
    æĥħ人
    -0.23
    odyn
    -0.23
    xaf
    -0.23
    POSITIVE LOGITS
    åıĺæį¢
    0.25
     taken
    0.24
     Swan
    0.23
    ãģĤãģ£ãģ¦
    0.23
    _MATRIX
    0.23
    LECTION
    0.23
     rated
    0.23
    å®ĥçļĦ
    0.23
    人éĢł
    0.23
     geliÅŁme
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.