© 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. 18-TRANSCODER-HP
    7. 88381
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    't
    -0.28
     lobby
    -0.26
    sworth
    -0.24
     droit
    -0.23
    uem
    -0.23
    ngth
    -0.23
     triple
    -0.23
     GPUs
    -0.23
    ãģ¾ãģ¾
    -0.23
     licensed
    -0.23
    POSITIVE LOGITS
    橹
    0.29
    ellig
    0.28
    |--
    0.28
    å¸Į
    0.26
    etical
    0.26
    ött
    0.25
    flation
    0.25
    ÑĦон
    0.25
    éĴ»çŁ³
    0.25
    æŶæķĪ
    0.24
    Activations Density 3.651%

    No Known Activations