© 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. 20-TRANSCODER-HP
    7. 64736
    Prev
    Next
    INDEX
    Explanations

    advantage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çļĦåģļæ³ķ
    -0.28
    구
    -0.26
    adopt
    -0.26
    åı·çłģ
    -0.26
    åĪĨåī²
    -0.25
    æĦ
    -0.25
    羣åģĩ
    -0.25
    ä¸įä¸Ĭ
    -0.25
    rq
    -0.24
    åı£
    -0.24
    POSITIVE LOGITS
    Smarty
    0.29
    å¾Īæ¼Ĥ亮
    0.25
    nerRadius
    0.25
    smarty
    0.24
    ,private
    0.24
    iola
    0.24
    .between
    0.24
     really
    0.23
     gab
    0.23
     scaffold
    0.23
    Activations Density 9.530%

    No Known Activations