© 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. 128968
    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
     setInput
    -0.25
     +↵↵
    -0.23
     Athletic
    -0.23
    æ¸ħç®Ĺ
    -0.23
    osit
    -0.23
    ÑĤелÑĮ
    -0.22
    ãģĵãģ¨ãģ§ãģĻ
    -0.22
    .asp
    -0.22
    phis
    -0.22
    åħ³èģĶ交æĺĵ
    -0.22
    POSITIVE LOGITS
    uc
    0.27
    çļĦ空éĹ´
    0.27
     smo
    0.26
    cate
    0.24
    åħ±äº§åħļåijĺ
    0.24
    .uc
    0.24
    à¸Ķาร
    0.23
    draft
    0.23
     edges
    0.23
     ÑĤекÑģÑĤ
    0.22
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.