© 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. 9828
    Prev
    Next
    INDEX
    Explanations

    Code and foreign languages

    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
    inic
    -0.28
    aine
    -0.27
    ä¹IJæĦı
    -0.27
    æľīå¤ļ大
    -0.26
    ת×Ļ×Ļ×Ŀ
    -0.26
    帼
    -0.25
     parte
    -0.25
    ucs
    -0.25
    å¾Ĥ
    -0.24
    OCR
    -0.24
    POSITIVE LOGITS
    æľº
    0.31
     gram
    0.27
    =*
    0.26
     UIImage
    0.26
    缮
    0.26
    éŁ³
    0.24
     enumerate
    0.23
    å§ļæĺİ
    0.23
    fty
    0.23
    ä¸ĺ
    0.23
    Activations Density 0.002%

    No Known Activations