© 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. 20-TRANSCODER-HP
    7. 142738
    Prev
    Next
    INDEX
    Explanations

    app

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    atta
    -0.28
     marked
    -0.27
    çķĮ
    -0.26
    .marker
    -0.25
    Advertisements
    -0.24
    çķĮçļĦ
    -0.24
    è®°èĢħåľ¨
    -0.24
    åIJĪä¸Ģ
    -0.24
    è®®é¢ĺ
    -0.23
    bout
    -0.23
    POSITIVE LOGITS
    alink
    0.27
    igator
    0.25
    ledon
    0.25
    ãģªãģıãģ¦ãĤĤ
    0.25
     Caldwell
    0.25
     Hide
    0.25
     اÙĦÙħÙĨت
    0.25
    ertools
    0.24
     infinitely
    0.23
     Locke
    0.23
    Activations Density 0.998%

    No Known Activations