© 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. 27-TRANSCODER-HP
    7. 9637
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     interaction
    -0.30
     interactions
    -0.29
     composition
    -0.28
    /workspace
    -0.27
    è¡Ģ液循çݯ
    -0.26
     interacting
    -0.26
     Kontakt
    -0.26
     administration
    -0.26
    aign
    -0.26
     scenario
    -0.25
    POSITIVE LOGITS
    åħ¨ä½ĵåijĺå·¥
    0.36
    客æĪ·æıIJä¾Ľ
    0.31
    让人们
    0.30
     civilians
    0.30
     individuals
    0.29
     employees
    0.29
    åŃ©åŃIJ们
    0.28
    客æĪ·çļĦ
    0.28
     customers
    0.28
    olk
    0.28
    Activations Density 0.012%

    No Known Activations