© 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. 23989
    Prev
    Next
    INDEX
    Explanations

    Medicare

    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
    responseData
    -0.27
    é£ŀæī¬
    -0.27
    é£Ľ
    -0.26
    ancell
    -0.26
     Derne
    -0.24
    ãģĻãĤĭãģĵãģ¨ãģ§
    -0.23
    STACK
    -0.23
     resultList
    -0.23
     ави
    -0.23
     constit
    -0.23
    POSITIVE LOGITS
    æľĽ
    0.28
    çŁ¢
    0.27
    sume
    0.27
    æ¶ī
    0.26
    ng
    0.26
     directed
    0.25
    许
    0.25
     cent
    0.25
    æķ°åŃĹåĮĸ
    0.25
    以为
    0.24
    Activations Density 0.003%

    No Known Activations