© 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. 99110
    Prev
    Next
    INDEX
    Explanations

    Code and formatting

    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
    论
    -0.27
    ERGY
    -0.26
    .au
    -0.26
    迹
    -0.26
    -python
    -0.25
     Aad
    -0.25
    forces
    -0.24
     Mention
    -0.24
    è«ĸ
    -0.23
    ÑĪение
    -0.23
    POSITIVE LOGITS
    ç§ijæĬĢèĤ¡ä»½
    0.26
    .directory
    0.25
     mornings
    0.25
    unda
    0.25
     gib
    0.24
    诡
    0.24
     TOP
    0.24
    geb
    0.24
    agog
    0.23
     Tops
    0.23
    Activations Density 0.006%

    No Known Activations