© 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. 89973
    Prev
    Next
    INDEX
    Explanations

    scientific, medical, technical documents

    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
    Not in Any Lists

    No Comments

    Negative Logits
     tim
    -0.28
    éĹª
    -0.27
    Æ¡
    -0.26
    çªľ
    -0.26
    éľİ
    -0.26
     voluntary
    -0.26
    ForResource
    -0.26
     orthodox
    -0.26
     ÑįкÑģп
    -0.25
     getNode
    -0.25
    POSITIVE LOGITS
    èĬĤå¥ı
    0.31
    çģı
    0.24
    æį§
    0.24
    éģĹæĨ¾
    0.23
    iero
    0.23
     LC
    0.23
     sublicense
    0.23
     pal
    0.23
    het
    0.23
    槿
    0.23
    Activations Density 3.903%

    No Known Activations