© 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. 62690
    Prev
    Next
    INDEX
    Explanations

    level

    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
    éĥ
    -0.27
     sigu
    -0.26
    æľīæĿ¡ä»¶çļĦ
    -0.25
    const
    -0.24
    /
    -0.23
     facult
    -0.23
    æĢĢ念
    -0.23
    лег
    -0.23
     long
    -0.23
    Seg
    -0.23
    POSITIVE LOGITS
    owitz
    0.28
     testcase
    0.27
    èĩ¾
    0.26
     ************************************************************************
    0.25
    主ä½ĵ责任
    0.25
    濯
    0.25
    ãĥĨãĤ£ãĥ³ãĤ°
    0.24
     troch
    0.24
    åī¯æľ¬
    0.24
    æŀ¢
    0.23
    Activations Density 1.016%

    No Known Activations