© 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. 129098
    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
     Fold
    -0.28
    ÑĪив
    -0.26
     interven
    -0.26
     retiring
    -0.25
     Educ
    -0.25
    轸
    -0.25
    飬
    -0.25
    æĥ¶
    -0.24
    Fold
    -0.24
    人å¿ĥ
    -0.24
    POSITIVE LOGITS
    çİĭåĽ½
    0.26
    phys
    0.25
    åľ¨æİ¥åıĹ
    0.25
    éĢļçŁ¥
    0.24
    éļľç¢į
    0.24
    ats
    0.24
    éĺ»
    0.24
    åľ¨çİ°åľº
    0.23
    alous
    0.23
    ight
    0.23
    Activations Density 53.355%

    No Known Activations

    This feature has no known activations.