© 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. 110983
    Prev
    Next
    INDEX
    Explanations

    or

    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
    ?,?,?,?,
    -0.32
    ãģ©ãĤĮ
    -0.29
    ials
    -0.29
     all
    -0.29
     None
    -0.29
    éĢIJä¸Ģ
    -0.28
    è¿Ļåĩłä¸ª
    -0.28
    æīĢæľī
    -0.28
    åħ¨æĸ¹ä½į
    -0.27
    None
    -0.26
    POSITIVE LOGITS
    两èĢħ
    0.97
    both
    0.94
     both
    0.93
    äºĮèĢħ
    0.90
    Both
    0.86
     Both
    0.86
    è¿Ļ两ç§į
    0.79
     BOTH
    0.76
    _both
    0.75
    è¿Ļ两个
    0.74
    Activations Density 0.005%

    No Known Activations