© 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. 27-TRANSCODER-HP
    7. 56369
    Prev
    Next
    INDEX
    Explanations

    school/education performance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    lig
    -0.31
    utow
    -0.30
    èѦæĥķ
    -0.26
     Lig
    -0.25
    "${
    -0.25
    :${
    -0.24
    éĻªåIJĮ
    -0.24
    æŃ£åĢ¼
    -0.24
    æĬµæĬĹ
    -0.24
    ç«Ļç«ĭ
    -0.24
    POSITIVE LOGITS
     performance
    0.30
    缩å°ı
    0.28
    æĢ§èĥ½
    0.28
    çIJIJ
    0.27
    performance
    0.27
    perse
    0.27
    è¯į
    0.27
    .aspect
    0.27
    è¯Ńæ³ķ
    0.27
    åı¥
    0.26
    Activations Density 0.002%

    No Known Activations