© 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. 9812
    Prev
    Next
    INDEX
    Explanations

    Locations and sports

    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
    ç»ıèIJ¥æ´»åĬ¨
    -0.27
     incidental
    -0.26
    æµģæĺŁ
    -0.25
    å©´
    -0.25
    èĪī
    -0.24
    鸥
    -0.24
    XMLElement
    -0.24
     presentations
    -0.24
    æ·±æ·±åľ°
    -0.24
    ursions
    -0.24
    POSITIVE LOGITS
    :Object
    0.26
    èĪIJ
    0.26
    èĮĥ
    0.26
     Tu
    0.25
    æķ´ä¸ª
    0.25
    лиÑĩ
    0.24
    åįĬ个
    0.24
    ward
    0.24
    wards
    0.24
    æķ´åĢĭ
    0.24
    Activations Density 0.111%

    No Known Activations