© 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. 140610
    Prev
    Next
    INDEX
    Explanations

    computer code/data

    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
     PURPOSE
    -0.26
    èµĸ
    -0.25
    ç¼Ģ
    -0.24
    飽
    -0.24
    èīºäºº
    -0.24
    tör
    -0.24
    ocator
    -0.24
     Sap
    -0.24
    æľīéĴĪ对æĢ§
    -0.23
    饶
    -0.23
    POSITIVE LOGITS
    uba
    0.28
    ä¸Ģå®ļæĺ¯
    0.26
    ijo
    0.26
    姥
    0.24
    ÐIJÐĹ
    0.24
    resa
    0.24
    è´ŁåĢº
    0.24
    pNet
    0.24
    ä¸Ģå®ļ
    0.24
    ൽ
    0.23
    Activations Density 16.347%

    No Known Activations