© 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. 19-TRANSCODER-HP
    7. 9399
    Prev
    Next
    INDEX
    Explanations

    News/legal text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ewis
    -0.30
     StatefulWidget
    -0.28
    æĻĭ
    -0.27
    èĤ¥
    -0.27
    å°ıå¿ĥ
    -0.25
    çĶ¨åĬĽ
    -0.25
    çļĦåѦçĶŁ
    -0.24
    æĸ§
    -0.24
    udent
    -0.23
     Escorts
    -0.23
    POSITIVE LOGITS
    зи
    0.29
    ä¸įå¾Ĺ转载
    0.28
    alo
    0.28
    oris
    0.27
    elly
    0.27
    oru
    0.26
    ĪæĿĥ
    0.26
    anie
    0.25
    åģ¿
    0.25
    _alg
    0.24
    Activations Density 0.014%

    No Known Activations