© 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. 20-TRANSCODER-HP
    7. 64740
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     neuronal
    -0.28
    encing
    -0.27
    é£İåIJ¹
    -0.27
    IJľ
    -0.26
    BW
    -0.26
    aging
    -0.26
     unc
    -0.25
    ç®Ń
    -0.25
    chin
    -0.25
    wich
    -0.25
    POSITIVE LOGITS
    ="<<
    0.26
    çķĮ第ä¸Ģ
    0.26
    æĴIJ
    0.26
    è¿Ļåıª
    0.24
    è¡Ķ
    0.24
    ogram
    0.24
    为空
    0.23
    _guid
    0.23
    åĪ°åºķ
    0.23
    顧
    0.23
    Activations Density 4.245%

    No Known Activations

    This feature has no known activations.