© 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. 106963
    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
    Not in Any Lists

    No Comments

    Negative Logits
    inia
    -0.28
    éļĪ
    -0.27
     perm
    -0.26
     Kendrick
    -0.26
     percentages
    -0.25
    edly
    -0.24
    _arch
    -0.24
     arcade
    -0.24
    åľ¨çݩ家
    -0.24
    reo
    -0.24
    POSITIVE LOGITS
    项
    0.29
     OPTION
    0.28
    oth
    0.27
    _VALUE
    0.27
    ή
    0.26
    ÃĿ
    0.26
    leased
    0.26
    ä¸Ģæĸ¹
    0.26
    cai
    0.25
    åıĮæĸ¹
    0.24
    Activations Density 7.015%

    No Known Activations

    This feature has no known activations.