© 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. 24183
    Prev
    Next
    INDEX
    Explanations

    duodenum, medical

    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
    ç«ŀèµĽ
    -0.26
    .Checked
    -0.26
    ServiceProvider
    -0.25
     competing
    -0.25
    æѤç§į
    -0.25
    æ³ħ
    -0.24
     squared
    -0.24
     пÑģ
    -0.24
    CHandle
    -0.24
    طر
    -0.24
    POSITIVE LOGITS
    że
    0.28
    æij©æīĺ
    0.28
    Buy
    0.26
    ä¼ĹçŃ¹
    0.26
    agma
    0.26
     syn
    0.26
    á»Ļ
    0.25
    com
    0.25
    æĹ©
    0.25
     moto
    0.24
    Activations Density 0.002%

    No Known Activations