© 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. 131024
    Prev
    Next
    INDEX
    Explanations

    General text snippets

    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
    è¿Ļæī¹
    -0.25
    以åIJİ
    -0.25
     hakkında
    -0.25
    ä»ĸçŁ¥éģĵ
    -0.25
    incinn
    -0.24
    å¾Īæĸ¹ä¾¿
    -0.24
    åŃ
    -0.24
     understand
    -0.24
    åĴĮä»ĸçļĦ
    -0.24
     gimm
    -0.23
    POSITIVE LOGITS
    dio
    0.35
    奥æŀĹåĮ¹åħĭ
    0.27
    (di
    0.25
    (Default
    0.25
    arih
    0.24
    yi
    0.24
    :frame
    0.24
    irs
    0.24
     Olympics
    0.23
    éĢĬ
    0.23
    Activations Density 15.649%

    No Known Activations