© 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. 86801
    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
     Rh
    -0.25
    仪
    -0.24
     app
    -0.24
    为人
    -0.24
     Benson
    -0.24
    è¯Ī
    -0.24
     Most
    -0.23
    对该
    -0.23
    æѤ类
    -0.23
    oa
    -0.23
    POSITIVE LOGITS
    arges
    0.25
    uffles
    0.25
     Vict
    0.24
    arging
    0.24
    rif
    0.23
    abetic
    0.23
     neighbour
    0.23
    INCT
    0.23
    SelectionMode
    0.23
     CBC
    0.23
    Activations Density 0.028%

    No Known Activations

    This feature has no known activations.