© 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. 129132
    Prev
    Next
    INDEX
    Explanations

    Code and identifiers

    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
     spins
    -0.28
    Ł¥
    -0.25
     parallels
    -0.24
    aceous
    -0.24
     intensified
    -0.23
     chin
    -0.23
    åĩºè½¨
    -0.23
    .twig
    -0.23
    \\\
    -0.23
    åįĥä¸ĩ
    -0.23
    POSITIVE LOGITS
    æ·ĭ
    0.35
    æľ¬æĬ¥
    0.31
    æĪijéĥ½
    0.29
    æĪijä»¬ä¹Ł
    0.27
    èĢĮåıĪ
    0.27
    åį´åıĪ
    0.26
     ..."↵↵
    0.26
     ..."↵
    0.26
    ç²Ĺ
    0.26
    quo
    0.26
    Activations Density 0.001%

    No Known Activations