© 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. 97200
    Prev
    Next
    INDEX
    Explanations

    categories of things

    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
    jo
    -0.28
    avn
    -0.25
    jam
    -0.25
     注æĦı
    -0.25
    Mean
    -0.25
    èĢĥè¯ģ
    -0.24
    erer
    -0.24
    æĽĿ
    -0.24
    lik
    -0.24
    Insensitive
    -0.23
    POSITIVE LOGITS
    è°ı
    0.26
    {:
    0.26
    cents
    0.25
    ulously
    0.25
    翻身
    0.24
    cente
    0.24
    åħ¬å¼Ģåıijè¡Į
    0.24
    èħ¾
    0.23
    主人
    0.23
     wireType
    0.23
    Activations Density 0.030%

    No Known Activations