© 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. 30229
    Prev
    Next
    INDEX
    Explanations

    4

    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
    opl
    -0.26
    ãģĹãģı
    -0.26
    bara
    -0.26
    een
    -0.25
    ëłī
    -0.25
    its
    -0.24
    cover
    -0.24
    .bias
    -0.24
    åįı
    -0.24
    翻身
    -0.24
    POSITIVE LOGITS
     closets
    0.25
    æĢİä¹Īèĥ½
    0.25
    æľį
    0.24
     ActionController
    0.24
    è¯ł
    0.24
    totalCount
    0.23
     Orchard
    0.23
     perfection
    0.23
    yon
    0.23
    ']}'
    0.23
    Activations Density 1.851%

    No Known Activations