© 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. 22-TRANSCODER-HP
    7. 86884
    Prev
    Next
    INDEX
    Explanations

    Protests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     daģı
    -0.29
    edException
    -0.28
     tie
    -0.27
     Tie
    -0.27
    ä¸įä¹ħ
    -0.25
    tie
    -0.24
    éĢłç¦ı
    -0.24
     ÑĦÑĥÑĤ
    -0.24
    CKET
    -0.24
     mist
    -0.24
    POSITIVE LOGITS
    åĽ¢ä¼Ļ
    0.24
     posters
    0.24
     Allen
    0.24
    allen
    0.24
    nos
    0.24
     modules
    0.24
     payroll
    0.24
     Modules
    0.23
     opportunities
    0.23
    Sal
    0.23
    Activations Density 0.003%

    No Known Activations