© 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. 57390
    Prev
    Next
    INDEX
    Explanations

    sports and games

    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
     sequential
    -0.85
     consecutive
    -0.81
     sequence
    -0.76
     sequentially
    -0.75
    ä¾Ŀ次
    -0.73
     Sequential
    -0.72
    è¿ŀç»Ń
    -0.71
    åºıåĪĹ
    -0.69
    sequential
    -0.65
     successive
    -0.65
    POSITIVE LOGITS
    å»ĭ
    0.28
    ButtonDown
    0.26
    irable
    0.25
    endo
    0.25
    æĮĩ令
    0.24
    tere
    0.24
    å¿Ĵ
    0.23
    æľ¬æĬ¥è®¯
    0.23
    enge
    0.23
    xies
    0.23
    Activations Density 0.003%

    No Known Activations