© 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. 62800
    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
    ä¸Ĭæľī
    -0.31
     beans
    -0.28
    ä¸ĬçļĦ
    -0.28
    å®Ŀè´Ŀ
    -0.25
     bean
    -0.24
    oves
    -0.24
    heels
    -0.24
     evacuated
    -0.24
    lius
    -0.24
    icator
    -0.23
    POSITIVE LOGITS
     Peninsula
    0.30
    ä¸įè¿ľ
    0.29
    éĢ¾
    0.29
    çļĦæĵįä½ľ
    0.27
    cura
    0.25
    Nd
    0.25
    æĵįä½ľ
    0.24
    .ib
    0.24
    asic
    0.24
    åIJĦè¡Į
    0.24
    Activations Density 0.169%

    No Known Activations

    This feature has no known activations.