© 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. 130933
    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
     disciplines
    -0.28
     obt
    -0.27
    á»Ģ
    -0.25
    秩
    -0.25
    æ¦Ĥ念
    -0.24
    éĿ¢åħ·
    -0.24
    atisf
    -0.23
    inda
    -0.23
     coll
    -0.23
     Glover
    -0.23
    POSITIVE LOGITS
    ŀĭ
    0.31
    øre
    0.25
    å°±è¿ij
    0.25
     darn
    0.24
    åijĥ
    0.24
     shin
    0.23
    åĭģ
    0.23
     ApplicationRecord
    0.23
     territorial
    0.23
    erguson
    0.23
    Activations Density 50.856%

    No Known Activations

    This feature has no known activations.