© 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. 42472
    Prev
    Next
    INDEX
    Explanations

    health/medical contexts

    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
    orthy
    -0.26
    [attr
    -0.26
    epy
    -0.25
     setattr
    -0.25
     freezes
    -0.25
    JOR
    -0.25
    åİ¢
    -0.24
    lex
    -0.24
    ta
    -0.24
    æĸ½å·¥çİ°åľº
    -0.24
    POSITIVE LOGITS
    åħ¬ç«ĭåĮ»éĻ¢
    0.35
    åį«çĶŁ
    0.33
     clinical
    0.32
    åį«çĶŁåģ¥åº·
    0.31
     health
    0.31
    åį«åģ¥
    0.31
    -health
    0.31
     Pump
    0.30
    Health
    0.29
     Krank
    0.29
    Activations Density 0.000%

    No Known Activations