© 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. 14-TRANSCODER-HP
    7. 41520
    Prev
    Next
    INDEX
    Explanations

    API requests and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     PROVIDED
    -0.26
    лем
    -0.26
    è´¨éĩı管çIJĨ
    -0.26
    骢
    -0.26
    nü
    -0.25
    irut
    -0.24
    ",__
    -0.24
    anko
    -0.24
    à¸Ĺà¸Ńà¸Ķ
    -0.24
    å¼Ģåĩº
    -0.24
    POSITIVE LOGITS
    çīĮ
    0.28
    讨
    0.28
    éĽī
    0.28
    odata
    0.26
    åĽł
    0.26
    éĩľ
    0.26
    ga
    0.25
    asurement
    0.24
    æĬĵä½ı
    0.24
    饮æĸĻ
    0.24
    Activations Density 1.056%

    No Known Activations