© 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. 99216
    Prev
    Next
    INDEX
    Explanations

    guidance

    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
    ToRemove
    -0.27
    磾
    -0.26
     compos
    -0.26
    omat
    -0.26
    ç½
    -0.26
    UIL
    -0.24
    æĪĺèĥľ
    -0.23
    çľ¼è¢ĭ
    -0.23
    æİĴæĸ¥
    -0.23
    iliate
    -0.23
    POSITIVE LOGITS
    ene
    0.31
     support
    0.27
     reg
    0.26
    ResourceManager
    0.25
    ansson
    0.25
    anas
    0.25
     Shed
    0.24
    áp
    0.24
     navigator
    0.24
     organ
    0.24
    Activations Density 0.002%

    No Known Activations