© 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. 30-TRANSCODER-HP
    7. 94998
    Prev
    Next
    INDEX
    Explanations

    Medical appointments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĩı
    -0.28
    IPAddress
    -0.27
    è¡Įä¸ļ
    -0.26
    å·¥ä¸ļåĮĸ
    -0.26
    jit
    -0.26
    jis
    -0.25
    ç½ij游
    -0.25
    ä¸ļ
    -0.25
    æĦŁ
    -0.25
    berg
    -0.24
    POSITIVE LOGITS
     appointments
    0.34
     screenings
    0.32
     trips
    0.29
     visits
    0.29
     recall
    0.29
     health
    0.29
     recalls
    0.28
    å°±è¯Ĭ
    0.28
     visit
    0.28
     information
    0.27
    Activations Density 0.895%

    No Known Activations