© 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. 113053
    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
    ä¸įåĪ©
    -0.28
     Clerk
    -0.25
     numeral
    -0.24
    è¿ĩå¾Ģ
    -0.24
    .ms
    -0.24
    ยาย
    -0.24
     Margin
    -0.23
     Arrow
    -0.23
    åĵı
    -0.23
    å¯ĵ
    -0.23
    POSITIVE LOGITS
    xit
    0.27
    æĦı大
    0.27
     alike
    0.26
    èĢħãģ¯
    0.26
    vil
    0.26
    åIJĦ级
    0.26
    æģ½
    0.26
     Urg
    0.25
    ä¸ĢæĿ¡é¾Ļ
    0.25
    vk
    0.24
    Activations Density 0.022%

    No Known Activations

    This feature has no known activations.