© 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. 7879
    Prev
    Next
    INDEX
    Explanations

    Personal experiences

    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
    -results
    -0.29
    æ¹®
    -0.28
    èµ¢å¾Ĺ
    -0.28
    åIJĥå¾Ĺ
    -0.27
     Lau
    -0.27
    leading
    -0.25
     Results
    -0.25
    venir
    -0.25
    ç»ĵæŀľ
    -0.25
    éħIJ
    -0.25
    POSITIVE LOGITS
     guilty
    0.33
    æľ¬äºº
    0.28
     Himself
    0.27
    æĬĬè¿ĻäºĽ
    0.26
     imp
    0.25
     simultaneously
    0.25
    Attach
    0.25
     willing
    0.25
    TOT
    0.25
    æѤæŶ
    0.24
    Activations Density 0.002%

    No Known Activations