© 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. 99227
    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
    æ°ı
    -0.29
    ä»ħä¾ĽåıĤèĢĥ
    -0.25
    é¹ħ
    -0.25
     PROF
    -0.24
     Pros
    -0.24
    顶
    -0.24
     Scheme
    -0.23
     floated
    -0.23
    å¼ı
    -0.22
    åħľ
    -0.22
    POSITIVE LOGITS
    _lc
    0.26
    _AG
    0.26
    wij
    0.25
    (common
    0.24
    lifting
    0.23
    _air
    0.23
     reacting
    0.23
    $criteria
    0.23
    -opacity
    0.23
     Kensington
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.