© 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. 24020
    Prev
    Next
    INDEX
    Explanations

    pancreatic beta cells and diabetes

    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
    agos
    -0.29
    èĥ¼
    -0.26
    åłķ
    -0.26
     пÑĢоÑģ
    -0.26
    orts
    -0.26
    Sibling
    -0.25
    =!
    -0.25
    -hole
    -0.25
    FolderPath
    -0.24
    uo
    -0.24
    POSITIVE LOGITS
    äºĶè¡Į
    0.33
    isper
    0.30
    人çī©
    0.28
     tiết
    0.27
    warts
    0.27
    å¦Ĥå®ŀ
    0.27
    isz
    0.27
    æĥij
    0.26
     Yosh
    0.26
    çķª
    0.24
    Activations Density 0.006%

    No Known Activations