© 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. 99266
    Prev
    Next
    INDEX
    Explanations

    Standards

    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
     unl
    -0.26
    .Syntax
    -0.26
     trông
    -0.25
     softened
    -0.24
    alsy
    -0.24
    åIJĦè¡Į
    -0.24
    è·ŁæĪij说
    -0.24
    çı¥
    -0.23
    åħĪ导
    -0.23
    perienced
    -0.23
    POSITIVE LOGITS
    äºĭä¸ļ
    0.29
    æĸĭ
    0.27
    TXT
    0.25
    nis
    0.24
    äºĮåŃĹ
    0.24
    åħ·æľī
    0.24
    ä¸ļ
    0.23
    nels
    0.23
    udev
    0.23
    ADIO
    0.23
    Activations Density 0.003%

    No Known Activations