© 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. 9931
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    antor
    -0.26
    oste
    -0.25
    éĽ¾
    -0.25
    潦
    -0.25
    æѦ
    -0.24
     wax
    -0.24
     description
    -0.23
    æĿ¾
    -0.23
    artz
    -0.23
    .apple
    -0.23
    POSITIVE LOGITS
    çīĪæľ¬
    0.27
     equivalents
    0.27
     counterparts
    0.27
    ä¼¼
    0.26
    çļĦè¶ĭåĬ¿
    0.25
     Version
    0.25
    综
    0.24
    _ONCE
    0.24
    åĪłéĻ¤æĪIJåĬŁ
    0.24
    æĦıåij³çĿĢ
    0.24
    Activations Density 0.008%

    No Known Activations