© 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. 113180
    Prev
    Next
    INDEX
    Explanations

    Code, essays, technical texts

    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
    å°±æĺ¯è¦ģ
    -0.26
    \Catalog
    -0.26
    ackets
    -0.25
    icit
    -0.24
    aligned
    -0.24
    acular
    -0.24
    -inner
    -0.23
    嶷
    -0.23
    èĬ¯
    -0.23
    ÑıÑĤÑģÑı
    -0.23
    POSITIVE LOGITS
    æĬij
    0.26
     Loves
    0.25
    datas
    0.25
    realm
    0.25
    fte
    0.25
     treff
    0.25
    éĽªå±±
    0.24
    hte
    0.24
    bomb
    0.23
    æĦı大
    0.23
    Activations Density 0.001%

    No Known Activations