© 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. 9-TRANSCODER-HP
    7. 29269
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    erness
    -0.26
    à¸ij
    -0.26
    ¢åįķ
    -0.26
    ä¸įåIJĮçļĦ
    -0.25
    дан
    -0.24
    aunch
    -0.24
    elines
    -0.24
     UIAlertController
    -0.24
    olic
    -0.23
    nea
    -0.23
    POSITIVE LOGITS
    ç«ĭæĸ¹
    0.27
    æĬ¥éħ¬
    0.25
    å¾
    0.25
     personnel
    0.24
    copyright
    0.24
     toured
    0.24
    ableObject
    0.24
    pur
    0.24
    çIJĨäºĭä¼ļ
    0.24
    è¿ĻäºĽäºº
    0.24
    Activations Density 4.792%

    No Known Activations