© 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. 12-TRANSCODER-HP
    7. 24093
    Prev
    Next
    INDEX
    Explanations

    medical conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Visibility
    -0.28
     Visibility
    -0.25
    Ñģо
    -0.25
    èŁł
    -0.25
    ised
    -0.25
     Pend
    -0.25
    åı¯è§Ĥ
    -0.24
    æİĮ声
    -0.24
    visibility
    -0.24
    FullName
    -0.23
    POSITIVE LOGITS
    æģ¤
    0.28
    rap
    0.25
    è¡«
    0.25
    èIJ½ä¸ĭ
    0.25
    çļĦ表çİ°
    0.25
     afr
    0.24
    INCT
    0.24
     Formal
    0.24
    çªĦ
    0.24
    æĶĴ
    0.24
    Activations Density 0.004%

    No Known Activations