© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 141161
    Prev
    Next
    INDEX
    Explanations

    Liver diseases

    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
    Not in Any Lists

    No Comments

    Negative Logits
    stown
    -0.27
    çļĦåīįæıIJä¸ĭ
    -0.25
     nonatomic
    -0.25
    lya
    -0.25
    _HERE
    -0.24
    æĤ¬å¿µ
    -0.24
    agara
    -0.24
    thur
    -0.24
    erva
    -0.24
    æ²¥
    -0.23
    POSITIVE LOGITS
     sire
    0.25
    æĮĩæĮ¥
    0.24
    æĬĽå¼ĥ
    0.23
     Walk
    0.23
    ç»ĻäºĪäºĨ
    0.23
    欢
    0.23
    èĭį
    0.23
    åĽŀé¦Ī
    0.23
     cac
    0.23
     discarded
    0.23
    Activations Density 1.970%

    No Known Activations