© 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. 32-TRANSCODER-HP
    7. 42668
    Prev
    Next
    INDEX
    Explanations

    electronic health records (EHR)

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç«ĭä½ĵ
    -0.28
    çķ´
    -0.27
    gó
    -0.26
    æĸĩæĺİ
    -0.26
    çĽĺ
    -0.26
    ernal
    -0.25
    rel
    -0.24
    ftar
    -0.24
    ä¸īç»´
    -0.24
    çŃĴ
    -0.24
    POSITIVE LOGITS
     tele
    0.36
     Electronic
    0.34
    Electronic
    0.33
    鼻åŃIJ
    0.29
    çĶµåŃIJ
    0.29
     treatment
    0.29
    bih
    0.28
    worthy
    0.28
    tele
    0.28
     Treatment
    0.28
    Activations Density 0.013%

    No Known Activations