© 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. 140752
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    mos
    -0.30
    uyen
    -0.26
    enger
    -0.26
    perience
    -0.25
    æµģ泪
    -0.25
    æĪijæĺ¯
    -0.24
    inality
    -0.23
    ç»ī
    -0.23
    /not
    -0.23
    onom
    -0.23
    POSITIVE LOGITS
    ican
    0.26
    izers
    0.24
    ório
    0.24
     communicator
    0.24
    asion
    0.24
    æĬķèµĦ人
    0.23
     libr
    0.23
    详ç»Ĩä»ĭç»į
    0.23
    	↵	↵	↵
    0.23
    éł
    0.23
    Activations Density 28.670%

    No Known Activations