© 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. 131055
    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
    isi
    -0.29
     %=
    -0.27
    hire
    -0.26
    鬼
    -0.24
     bears
    -0.24
    glyphicon
    -0.24
    åĩ¡
    -0.23
    ddy
    -0.23
    èĥĨ
    -0.23
     ìĻ
    -0.23
    POSITIVE LOGITS
    æĻĮ
    0.28
    éªĦ
    0.25
    æĥ³åĪ°
    0.25
    felt
    0.25
     khuyến
    0.24
     Kov
    0.24
    çĥŃ度
    0.24
    xCC
    0.23
    à¸ķà¸ģ
    0.23
    ahlen
    0.23
    Activations Density 4.364%

    No Known Activations

    This feature has no known activations.