© 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. 90142
    Prev
    Next
    INDEX
    Explanations

    policy

    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
     advoc
    -0.29
    NST
    -0.27
    çĵ®
    -0.27
    åľ¨åIJĮä¸Ģ
    -0.27
    Including
    -0.26
    weis
    -0.25
     Including
    -0.24
    toast
    -0.24
     Quarter
    -0.24
    IFEST
    -0.24
    POSITIVE LOGITS
     Broken
    0.25
     hyper
    0.25
    æ³Ľ
    0.25
     circum
    0.25
     fur
    0.25
    liqu
    0.24
     hand
    0.24
    æľīæĽ´å¥½çļĦ
    0.24
    æīĭéĩĮ
    0.24
     commission
    0.24
    Activations Density 2.860%

    No Known Activations