© 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. 110918
    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
    oupon
    -0.28
    tings
    -0.24
    éĵĹ
    -0.23
     inquire
    -0.23
    umd
    -0.23
    ziaÅĤ
    -0.22
    chsel
    -0.22
    æĦıåIJij
    -0.22
     theat
    -0.21
    hiro
    -0.21
    POSITIVE LOGITS
    wins
    0.30
    ends
    0.24
    -Q
    0.24
     PROT
    0.22
    Prototype
    0.22
    èĮľ
    0.22
    SEP
    0.22
    riter
    0.21
    ç§ĺ书éķ¿
    0.21
     growing
    0.21
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.