© 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. 88111
    Prev
    Next
    INDEX
    Explanations

    Sentence beginnings

    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
    fan
    -0.27
    FFFF
    -0.27
    离å¼ĢäºĨ
    -0.27
    naires
    -0.25
    aight
    -0.25
    incess
    -0.25
    ffff
    -0.25
    ç±»åŀĭçļĦ
    -0.25
    çIJ´
    -0.24
    aintenance
    -0.23
    POSITIVE LOGITS
    çĥŃéĶĢ
    0.28
    æĢ»ä»·
    0.26
     Tobias
    0.26
    æļ´æ¶¨
    0.26
     rev
    0.25
    èIJ¥éĶĢ
    0.25
    ç«ŀäºī
    0.25
    让大家
    0.25
    议论
    0.25
     slippery
    0.24
    Activations Density 3.600%

    No Known Activations