© 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. 30358
    Prev
    Next
    INDEX
    Explanations

    African

    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
    å¢Ļ
    -0.26
    aul
    -0.25
    è¦ģ说
    -0.24
     sky
    -0.24
    éĭ
    -0.24
    æľŃ
    -0.24
    -not
    -0.23
    æľīæľºä¼ļ
    -0.23
    avar
    -0.23
    ãģ©ãģĵãĤį
    -0.23
    POSITIVE LOGITS
    esian
    0.28
    agini
    0.28
    unan
    0.27
    UCK
    0.26
    ÐĵлавнаÑı
    0.26
    ÑĮÑİ
    0.25
    ESIS
    0.25
    åģ¥åħ¨
    0.24
    ossal
    0.24
    çļĦæĪIJéķ¿
    0.24
    Activations Density 0.785%

    No Known Activations