© 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. 29329
    Prev
    Next
    INDEX
    Explanations

    code and names

    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
    ìĦ
    -0.26
     Hospital
    -0.26
    å¼ģ
    -0.25
     бил
    -0.25
     coron
    -0.24
    åł¡
    -0.24
     lim
    -0.23
     hospitalized
    -0.23
    hospital
    -0.23
    зи
    -0.23
    POSITIVE LOGITS
     Starter
    0.29
    ä¸Ģ天
    0.27
    inct
    0.27
    ä¸Ģ身
    0.27
    issance
    0.27
    Constraints
    0.27
    venient
    0.27
     material
    0.26
    ÑģÑĤоÑı
    0.25
    æĿIJæĸĻ
    0.25
    Activations Density 0.219%

    No Known Activations