© 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. 9642
    Prev
    Next
    INDEX
    Explanations

    code/filepaths/foreign language

    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
     said
    -0.33
     singleton
    -0.28
    said
    -0.28
     condu
    -0.26
     Said
    -0.26
    amental
    -0.26
     provinces
    -0.26
    祺
    -0.25
    说
    -0.25
     discrete
    -0.25
    POSITIVE LOGITS
    åŀĤ
    0.29
    etrize
    0.28
    èĤ©èĨĢ
    0.26
    å·²åľ¨
    0.26
    å·²äºİ
    0.26
    .problem
    0.25
    æĪ¿
    0.25
    ãĤ¹ãĥļ
    0.24
    azÄĥ
    0.24
     Await
    0.24
    Activations Density 0.885%

    No Known Activations