© 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. 112920
    Prev
    Next
    INDEX
    Explanations

    like

    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
     altogether
    -0.39
    æŁIJç§įç¨ĭ度
    -0.36
     knowingly
    -0.32
    æľ¬è´¨ä¸Ĭ
    -0.32
     fundamentally
    -0.32
    ä¸Ģå®ļç¨ĭ度
    -0.29
    æĪĸå¤ļæĪĸå°ij
    -0.29
     briefly
    -0.28
     essentially
    -0.28
     ultimately
    -0.28
    POSITIVE LOGITS
    rum
    0.27
    ãĢĮ
    0.26
    æĪIJ人
    0.26
    家åºŃ
    0.25
    çĶŁæ´»åľ¨
    0.24
    “
    0.24
    æľºä¼ļ
    0.24
    [].
    0.24
    çļĦæľºä¼ļ
    0.24
    achable
    0.24
    Activations Density 0.005%

    No Known Activations