© 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. 140765
    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
    echa
    -0.30
    agh
    -0.26
    oga
    -0.25
    设æĸ½å»ºè®¾
    -0.25
    acao
    -0.24
    PasswordField
    -0.24
    vern
    -0.24
    -io
    -0.24
     Hust
    -0.24
    ivial
    -0.23
    POSITIVE LOGITS
    èĥ¸
    0.31
     memoir
    0.28
     Thor
    0.25
    åŃĹåı·
    0.25
     hes
    0.24
     Tap
    0.24
    åĬ¨åĬĽ
    0.24
    æĥ³ä¸įåĪ°
    0.24
    ammad
    0.24
    Thor
    0.24
    Activations Density 25.663%

    No Known Activations

    This feature has no known activations.