© 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. 27-TRANSCODER-HP
    7. 7736
    Prev
    Next
    INDEX
    Explanations

    chronic diseases/health risk

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éļĪ
    -0.29
    è§Ĩ线
    -0.26
    мо
    -0.25
    =*/
    -0.24
    »¿
    -0.24
    enery
    -0.24
    IOD
    -0.24
    FI
    -0.24
    çļĦ缮åħī
    -0.24
    mare
    -0.24
    POSITIVE LOGITS
     chronic
    0.48
    æħ¢æĢ§
    0.47
     risk
    0.44
    chron
    0.44
     Risk
    0.42
     diabetes
    0.42
    risk
    0.41
    é«ĺè¡Ģåİĭ
    0.41
    åį±éĻ©
    0.41
    Risk
    0.39
    Activations Density 0.083%

    No Known Activations