© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 9194
    Prev
    Next
    INDEX
    Explanations

    foreign characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĮł
    -0.27
    å¾Ĺ罪
    -0.26
    çľ¼çļ®
    -0.25
    виз
    -0.25
    æģ°å¥½
    -0.25
     Advantage
    -0.25
    ä¸ŃåĽ½æĸĩåĮĸ
    -0.24
    æľĢåIJİä¸Ģ次
    -0.24
    [((
    -0.24
    溢
    -0.24
    POSITIVE LOGITS
    缮åīį
    0.34
    umbo
    0.30
     existing
    0.30
     currently
    0.30
    æĪIJçĨŁçļĦ
    0.29
     commercially
    0.29
    缮åīį为æŃ¢
    0.28
    ä»įæľª
    0.28
    çİ°æľīçļĦ
    0.28
     recently
    0.28
    Activations Density 0.004%

    No Known Activations