© 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. 88475
    Prev
    Next
    INDEX
    Explanations

    healthcare

    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
    anean
    -0.30
    æ¼Ķ
    -0.29
    olis
    -0.26
    åĪ¶
    -0.26
     thumbs
    -0.25
     Sic
    -0.24
    åĨħ容
    -0.24
     div
    -0.24
     theater
    -0.24
    äº
    -0.23
    POSITIVE LOGITS
    为æĤ¨æıIJä¾Ľ
    0.28
    è·Łä½ł
    0.28
    chez
    0.27
    horia
    0.26
    sell
    0.26
    对åѦçĶŁ
    0.26
    ousands
    0.25
    RANDOM
    0.25
    èį¤
    0.25
    é²ľèī³
    0.25
    Activations Density 14.557%

    No Known Activations