© 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. 24186
    Prev
    Next
    INDEX
    Explanations

    genetics and statistics

    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
    èIJ½åĪ°å®ŀå¤Ħ
    -0.28
    TestClass
    -0.27
    设计æĸ¹æ¡Ī
    -0.25
    çŃĸåĪĴ
    -0.25
    //}↵
    -0.25
    çİĩåħĪ
    -0.25
    ctal
    -0.25
     chù
    -0.25
    uttle
    -0.24
     embodied
    -0.24
    POSITIVE LOGITS
    容éĩı
    0.30
    opath
    0.27
    ndo
    0.27
    éģĵ
    0.26
    meer
    0.26
    Fed
    0.26
    ulings
    0.25
    ior
    0.25
     Father
    0.25
    ç²½
    0.25
    Activations Density 0.002%

    No Known Activations