© 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. 140644
    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
    è¯Ŀ
    -0.33
    mist
    -0.31
    ouis
    -0.29
    Club
    -0.29
    æĮĩ
    -0.29
     Club
    -0.29
    club
    -0.26
    çĿĽ
    -0.26
    å¼Ĥ
    -0.26
    û
    -0.26
    POSITIVE LOGITS
    Fold
    0.28
     fold
    0.27
    fold
    0.26
    åıijéħµ
    0.25
    纥
    0.24
    _WP
    0.24
    ias
    0.24
    å¢Ģ
    0.24
     rents
    0.24
     bake
    0.23
    Activations Density 26.274%

    No Known Activations

    This feature has no known activations.